© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 13340
    Prev
    Next
    INDEX
    Explanations

    C++ programming library components

    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
     ewigen
    -1.25
     cimetière
    -1.23
    jenigen
    -1.23
    惱
    -1.23
    βο
    -1.23
    訝
    -1.23
    躋
    -1.22
    韁
    -1.22
    蛻
    -1.22
    鑄
    -1.22
    POSITIVE LOGITS
     it
    1.78
     от
    1.38
     of
    1.25
    bidden
    1.23
     or
    1.18
    _
    1.17
     что
    1.16
     in
    1.16
    *
    1.16
     not
    1.16
    Activations Density 0.194%

    No Known Activations