© 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. 60305
    Prev
    Next
    INDEX
    Explanations

    export const declarations

    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
    .
    -1.89
    骉
    -1.84
     what
    -1.73
     véritable
    -1.65
    های
    -1.63
    와
    -1.56
    暃
    -1.52
     acepción
    -1.49
     pracuje
    -1.49
     inspiração
    -1.48
    POSITIVE LOGITS
    彼は
    1.66
     obwohl
    1.63
     несмотря
    1.59
    although
    1.58
     églises
    1.57
    ↵
    1.52
    </b>
    1.51
    </em>
    1.48
     "
    1.46
     Although
    1.46
    Activations Density 0.002%

    No Known Activations