© 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. 129153
    Prev
    Next
    INDEX
    Explanations

    any or anything

    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
     of
    -2.31
     also
    -2.19
     également
    -1.84
     ebenfalls
    -1.78
     similarly
    -1.70
     Insets
    -1.66
     likewise
    -1.57
     thereafter
    -1.48
     then
    -1.48
     observado
    -1.48
    POSITIVE LOGITS
    !
    1.86
     възможно
    1.71
    ;
    1.61
    ;
    1.55
    ont
    1.54
    cún
    1.53
    <bos>
    1.52
     juega
    1.50
     Atención
    1.46
    )
    1.45
    Activations Density 0.047%

    No Known Activations