© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 55879
    Prev
    Next
    INDEX
    Explanations

    numerical scores and results

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

    The neuron specializes in spotting numeric match‐score details (e.g. set scores like “6-3” and other sports result numbers).

    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
    What
    -0.84
    ائن
    -0.81
    Full
    -0.79
    ERT
    -0.78
    هر
    -0.78
    М
    -0.78
    getFloat
    -0.77
    ΩΝ
    -0.76
     Full
    -0.76
    Secondary
    -0.75
    POSITIVE LOGITS
    APPENDICES
    0.90
     حركة
    0.83
    Barriers
    0.82
    希望能
    0.81
    crush
    0.79
    维基
    0.78
    roomId
    0.77
     overpowering
    0.77
    STUDIES
    0.77
    ditto
    0.76
    Activations Density 0.016%

    No Known Activations