© 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. 128988
    Prev
    Next
    INDEX
    Explanations

    dates and numbers

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

    This neuron strongly activates on structural elements like section‐heading tokens and list or title numbers (e.g. numbered headings, article labels, and other standalone numeric or heading words).

    oai_token-act-pair · o4-miniTriggered 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
     with
    -1.98
     teilweise
    -1.55
     besonders
    -1.54
     as
    -1.53
     or
    -1.50
     oddly
    -1.49
     markedly
    -1.49
     overtly
    -1.48
     cleverly
    -1.47
     neatly
    -1.46
    POSITIVE LOGITS
    你先
    1.58
    圌
    1.53
     herrera
    1.52
    ⩽
    1.48
     après
    1.40
    却被
    1.38
     Chaque
    1.38
    涑
    1.37
    你是不是
    1.35
    \%,
    1.35
    Activations Density 0.008%

    No Known Activations