© 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. 34-GEMMASCOPE-RES-131K
    7. 31000
    Prev
    Next
    INDEX
    Explanations

    Olympic weightlifting and exercises

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

    The neuron strongly activates on numeric tokens (digits, years, weights, and other numeric data).

    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
    ื่น
    -0.75
    spf
    -0.74
    ɛ
    -0.73
    hringer
    -0.73
    フォー
    -0.73
    posis
    -0.73
     tanda
    -0.69
    游戏
    -0.68
     formación
    -0.68
     GetEnumerator
    -0.68
    POSITIVE LOGITS
     snatch
    1.52
     snatched
    1.11
     weight
    1.09
    Weight
    1.03
     snat
    0.97
     barbell
    0.96
     Weight
    0.95
     Olympic
    0.94
     Sn
    0.93
     olympic
    0.93
    Activations Density 0.011%

    No Known Activations