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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-262K
    7. 41487
    Prev
    Next
    INDEX
    Explanations

    generally recommended or preferred

    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
    ário
    0.76
     ежедневно
    0.76
    
    0.76
    MSFontService
    0.73
     خلال
    0.73
    ivez
    0.72
    
    0.72
     первые
    0.70
    <unused995>
    0.70
     fotografía
    0.70
    POSITIVE LOGITS
     ہے
    0.83
     für
    0.77
    )،
    0.77
     Änderung
    0.74
    )
    0.74
     isinstance
    0.73
     dla
    0.73
    )，
    0.70
     sinnvoll
    0.70
     для
    0.70
    Activations Density 0.061%

    No Known Activations