© 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. 39763
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and computations

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

    The neuron fires on numeric tokens representing decimal numbers (numbers with a fractional “.…” part).

    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
    Approximately
    -1.81
     ถ้า
    -1.80
    ↵↵
    -1.80
    Once
    -1.71
     içeris
    -1.65
     மற்றும்
    -1.60
     arasındaki
    -1.60
    沨
    -1.56
    鋅
    -1.56
     langen
    -1.56
    POSITIVE LOGITS
     was
    2.38
    \
    1.86
    only
    1.83
     doesn
    1.80
    骉
    1.76
    <bos>
    1.74
     wasn
    1.73
    .,"
    1.72
    like
    1.68
    桫
    1.68
    Activations Density 0.074%

    No Known Activations