© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-262K
    7. 11778
    Prev
    Next
    INDEX
    Explanations

    torrent sites and clients

    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
    с
    1.07
    ς
    1.07
    みました
    1.03
    ع
    0.98
    dır
    0.96
    ні
    0.96
    のでしょうか
    0.94
     quotidienne
    0.93
    irical
    0.93
     parecen
    0.92
    POSITIVE LOGITS
    musik
    1.23
    truck
    1.14
    r
    1.14
    ل
    1.12
    mies
    1.11
    stopper
    1.10
    ول
    1.09
    tions
    1.09
    ל
    1.08
    Ч
    1.07
    Activations Density 0.002%

    No Known Activations