© 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. 22579
    Prev
    Next
    INDEX
    Explanations

    class of

    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
    Not in Any Lists

    No Comments

    Negative Logits
    ⚢
    -1.45
    usehen
    -1.40
    
    -1.34
    を行います
    -1.33
    ⛦
    -1.32
    ౧
    -1.32
    螃
    -1.28
    Edo
    -1.27
     député
    -1.27
     الحل
    -1.27
    POSITIVE LOGITS
     of
    1.98
     that
    1.96
    ),
    1.81
     with
    1.72
    </h3>
    1.70
     but
    1.56
    </sub>
    1.43
    There
    1.42
     there
    1.42
    At
    1.41
    Activations Density 0.126%

    No Known Activations