© 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. 55593
    Prev
    Next
    INDEX
    Explanations

    highest average scorer

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

    The neuron activates on numeric statistics—particularly counts and figures (runs, matches, wickets, years, etc.) in cricket‐player summaries.

    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
     their
    -0.74
    DOP
    -0.73
     swear
    -0.73
    annin
    -0.72
     visibly
    -0.72
    漣
    -0.71
    balho
    -0.70
     berasal
    -0.69
    fitrión
    -0.69
    ̾
    -0.69
    POSITIVE LOGITS
     Aggregate
    1.01
     average
    0.96
    éens
    0.95
    average
    0.93
    umenical
    0.90
     Average
    0.88
     averages
    0.86
     AVERAGE
    0.86
     averaging
    0.85
    highest
    0.85
    Activations Density 0.023%

    No Known Activations