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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 83739
    Prev
    Next
    INDEX
    Explanations

    code and technical descriptions

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

    The neuron fires on numeric literals (sequences of digits) 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
     därför
    -0.86
     gré
    -0.83
    çage
    -0.78
     snabb
    -0.77
     äldre
    -0.77
     Yoruba
    -0.76
     取付
    -0.76
     säkert
    -0.75
     répé
    -0.75
    unjukkan
    -0.74
    POSITIVE LOGITS
    int
    1.16
    boolean
    1.14
    if
    1.02
    float
    1.00
     boolean
    0.91
     float
    0.86
     already
    0.82
     welcomed
    0.82
    label
    0.81
    落在
    0.80
    Activations Density 0.001%

    No Known Activations