© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 73658
    Prev
    Next
    INDEX
    Explanations

    classification categories

    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
     before
    -1.42
     only
    -1.42
     if
    -1.39
    どんな
    -1.33
     who
    -1.33
    abaikan
    -1.32
    Etimo
    -1.30
     in
    -1.27
     persona
    -1.27
     should
    -1.23
    POSITIVE LOGITS
     the
    1.85
    including
    1.63
     Songtext
    1.57
     trám
    1.48
     garantizar
    1.38
     überprü
    1.37
     incluyendo
    1.29
     either
    1.29
     brindar
    1.27
     incluindo
    1.26
    Activations Density 0.041%

    No Known Activations