© 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-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 73568
    Prev
    Next
    INDEX
    Explanations

    code and statements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    =
    -1.05
    Dll
    -1.03
     what
    -1.03
     ataupun
    -1.00
    ҽ
    -0.98
    *
    -0.98
    ---
    -0.98
     reú
    -0.97
     sebagaimana
    -0.97
     with
    -0.97
    POSITIVE LOGITS
    each
    1.17
     they
    1.12
    良いです
    1.09
    only
    1.03
     it
    1.02
    will
    0.98
    lo
    0.94
    once
    0.94
    few
    0.93
    みたいです
    0.93
    Activations Density 0.019%

    No Known Activations