© 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. 8797
    Prev
    Next
    INDEX
    Explanations

    speech and acoustic performance metrics

    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
     tylko
    -1.35
     molte
    -1.30
     splendid
    -1.28
    してみると
    -1.27
    !!!!!!!
    -1.27
    unico
    -1.26
     participer
    -1.24
     actually
    -1.23
     dieci
    -1.23
     самом
    -1.23
    POSITIVE LOGITS
     with
    1.36
    \
    1.23
    fiques
    1.20
    ciclopedia
    1.16
    forName
    1.13
    ())->
    1.07
    illés
    1.07
    liable
    1.07
     femen
    1.04
     trafic
    1.03
    Activations Density 0.050%

    No Known Activations