© 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. 36337
    Prev
    Next
    INDEX
    Explanations

    explain

    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
    եր
    1.98
    ς
    1.97
    ों
    1.82
    ು
    1.82
    ил
    1.78
     Ն
    1.77
    я
    1.74
    おります
    1.73
    此之外
    1.72
    ю
    1.72
    POSITIVE LOGITS
    ية
    2.86
    as
    2.31
    i
    2.16
    os
    1.98
    is
    1.96
    at
    1.93
    id
    1.86
    r
    1.85
    ian
    1.83
    ay
    1.75
    Activations Density 0.009%

    No Known Activations