© 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. 40148
    Prev
    Next
    INDEX
    Explanations

    weight classes and championships

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

    The neuron activates on mentions of fighters’ weight divisions (e.g. “bantamweight,” “featherweight,” “welterweight,” “light heavyweight”).

    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
      
    -1.83
     other
    -1.80
    </b>
    -1.77
     what
    -1.71
    ↵↵↵
    -1.57
     those
    -1.56
    ↵↵↵↵
    -1.53
    {
    -1.52
     others
    -1.49
     different
    -1.47
    POSITIVE LOGITS
     extraordinaire
    1.52
    Статья
    1.42
    لباس
    1.41
    criptures
    1.41
    essica
    1.38
    Đây
    1.38
    (!__
    1.37
    Zubereitung
    1.36
    Подроб
    1.36
    ஜ
    1.32
    Activations Density 0.015%

    No Known Activations