© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 86319
    Prev
    Next
    INDEX
    Explanations

    code symbols and punctuation

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

    The neuron responds to numeric literals—especially decimal numbers or percentages—in the text.

    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
    -
    -1.92
    0
    -1.88
    1
    -1.85
     
    -1.83
    to
    -1.80
    is
    -1.71
    de
    -1.63
    u
    -1.56
    ↵↵
    -1.54
     gesche
    -1.53
    POSITIVE LOGITS
    ſelves
    1.89
     and
    1.77
     also
    1.74
    vantaged
    1.73
    lusst
    1.66
    iguity
    1.65
     pulsante
    1.60
    毽
    1.59
    ISIONS
    1.59
     zelo
    1.58
    Activations Density 0.001%

    No Known Activations