© 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. 34-GEMMASCOPE-RES-131K
    7. 49246
    Prev
    Next
    INDEX
    Explanations

    numeric or numerical data

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

    The neuron fires on numeric literals—i.e. digit sequences or number tokens—in code or 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_34/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
    isEqual
    -0.83
    auda
    -0.81
     సౌ
    -0.74
     lengua
    -0.72
    теры
    -0.71
    顱
    -0.71
    acic
    -0.70
     Chaucer
    -0.70
    ператор
    -0.70
    PendingIntent
    -0.69
    POSITIVE LOGITS
     numeric
    2.22
     numerical
    2.11
    numeric
    1.91
    Numeric
    1.83
    数字
    1.77
     numbers
    1.77
     Numerical
    1.77
    numerical
    1.73
     Numeric
    1.73
    isdigit
    1.70
    Activations Density 0.036%

    No Known Activations