© 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
    3. Gemma-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-262K
    7. 5610
    Prev
    Next
    INDEX
    Explanations

    downward movement

    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
    .
    0.97
    AD
    0.90
    檚
    0.89
    *
    0.88
     worthwhile
    0.86
    ক
    0.84
     académ
    0.84
    _
    0.83
     case
    0.83
    ్‌
    0.82
    POSITIVE LOGITS
    ról
    0.99
    ﺩ
    0.97
    stairs
    0.97
    是指
    0.95
    ایج
    0.94
    บน
    0.93
    ทะเบียน
    0.92
    없는
    0.91
     وعلى
    0.91
    rith
    0.90
    Activations Density 0.172%

    No Known Activations