© 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. 45712
    Prev
    Next
    INDEX
    Explanations

    hands, leadership, pen names

    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
     said
    -1.43
     in
    -1.32
     to
    -1.30
     were
    -1.24
     while
    -1.23
     gekenn
    -1.15
    ladiator
    -1.13
     lanza
    -1.13
     for
    -1.10
    cises
    -1.10
    POSITIVE LOGITS
    嘀
    1.28
     گرفتن
    1.22
     bandar
    1.22
    ത്ര
    1.19
     grossa
    1.17
    issements
    1.14
     pollo
    1.14
     atmosfera
    1.11
     pukul
    1.09
     réfrigérateur
    1.09
    Activations Density 0.039%

    No Known Activations