© 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. 15727
    Prev
    Next
    INDEX
    Explanations

    XML, code, and technical documentation

    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
    );
    -1.53
     errado
    -1.34
     its
    -1.33
     atentos
    -1.31
    再加上
    -1.30
     fraught
    -1.28
     anche
    -1.27
     =
    -1.26
    嬷
    -1.24
     รัก
    -1.23
    POSITIVE LOGITS
     that
    2.00
    That
    1.48
    This
    1.41
    Thus
    1.32
     things
    1.32
     this
    1.32
     kostet
    1.31
     Vainqueur
    1.31
    While
    1.30
    However
    1.29
    Activations Density 0.001%

    No Known Activations