© 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. 5740
    Prev
    Next
    INDEX
    Explanations

    feature analysis and engineering

    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
    ه
    2.17
    ி
    2.16
    i
    2.05
    ’
    1.95
     Constitu
    1.88
    เรา
    1.84
     CLL
    1.84
    ઓ
    1.84
     continua
    1.76
    g
    1.73
    POSITIVE LOGITS
     prominently
    2.73
    pronged
    2.39
    ্সের
    2.03
    point
    1.98
    ból
    1.95
    column
    1.91
    palm
    1.91
    mortem
    1.91
    przy
    1.77
    leri
    1.73
    Activations Density 0.037%

    No Known Activations