© 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. 40510
    Prev
    Next
    INDEX
    Explanations

    MIT license

    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
     mislead
    0.98
     authorizes
    0.93
    ੀ
    0.93
     Ecosystem
    0.93
    rit
    0.91
     convain
    0.89
     Option
    0.88
     prerequisite
    0.88
     monsieur
    0.88
     debilitating
    0.87
    POSITIVE LOGITS
    ین
    1.19
    ول
    1.18
    よう
    1.06
    ج
    1.04
    ാമ
    1.01
    年份
    1.01
    完了
    0.98
    ла
    0.97
    icules
    0.95
    ok
    0.95
    Activations Density 0.000%

    No Known Activations