© 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. 134
    Prev
    Next
    INDEX
    Explanations

    most common / longest / best

    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
    ン
    0.90
    нің
    0.83
     cellulaire
    0.82
    quele
    0.81
    रेशन
    0.76
    scopic
    0.72
    ার
    0.71
     Счет
    0.71
    er
    0.70
    нең
    0.70
    POSITIVE LOGITS
    est
    0.95
    F
    0.95
    á
    0.94
    のである
    0.94
    こと
    0.93
    ത്
    0.91
    aurant
    0.91
    s
    0.91
    های
    0.89
    iest
    0.89
    Activations Density 0.577%

    No Known Activations