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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-262K
    7. 3618
    Prev
    Next
    INDEX
    Explanations

    submit buttons

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_12_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ez
    2.16
    equilibrium
    1.89
    ech
    1.86
    {
    1.86
    ${
    1.77
     emir
    1.77
    //*
    1.73
    ek
    1.72
    isn
    1.71
     influx
    1.70
    POSITIVE LOGITS
    ки
    2.20
    ছেন
    2.08
    jų
    2.06
    с
    1.95
    ف
    1.95
    いた
    1.88
    д
    1.88
    ले
    1.88
    го
    1.86
    ция
    1.85
    Activations Density 0.009%

    No Known Activations