© 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. 10-GEMMASCOPE-RES-131K
    7. 6828
    Prev
    Next
    INDEX
    Explanations

    repairs and renovations

    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_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     园
    -2.08
     jesús
    -2.03
    ⦊
    -1.98
     ヶ
    -1.93
     posY
    -1.91
     Many
    -1.88
     }));
    -1.85
    </h2>
    -1.84
    鹟
    -1.82
    翾
    -1.82
    POSITIVE LOGITS
    a
    2.27
    籥
    2.23
    ㈬
    2.17
     quintessential
    2.13
     breathtaking
    2.11
    </u>
    2.06
    ef
    2.03
    整个人
    2.00
     tumultuous
    1.98
    訁
    1.96
    Activations Density 0.003%

    No Known Activations