© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 100078
    Prev
    Next
    INDEX
    Explanations

    WELL, HYBRID, LUNCH, A

    np_acts-logits-general · gemini-2.5-flash-lite

    This neuron detects standalone section headings or list-item markers (e.g. numbered or titled subsection labels).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    The neuron is picking out standalone numeric tokens (numbers or quantities) in the text.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    standalone decimal numbers (often fractional) used as section markers, measurements, or scores.

    oai_token-act-pair · gpt-5Triggered by @jyhe0408

    line breaks or whitespace between distinct sections or list items in structured text.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     this
    -2.11
     each
    -1.74
     will
    -1.57
    heureusement
    -1.56
    今夜
    -1.49
     After
    -1.48
    ccccccc
    -1.38
    kitab
    -1.34
     and
    -1.33
    ppb
    -1.33
    POSITIVE LOGITS
     största
    1.72
     vardı
    1.71
    主に
    1.70
    ly
    1.66
    munity
    1.66
     زیرا
    1.63
    ol
    1.61
    来不及
    1.58
     где
    1.58
    </tr>
    1.57
    Activations Density 0.008%

    No Known Activations