© 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. 12976
    Prev
    Next
    INDEX
    Explanations

    Now that

    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
     by
    -2.03
     not
    -1.76
     will
    -1.68
     just
    -1.64
     $
    -1.63
     as
    -1.52
     did
    -1.51
    -1.42
     {
    -1.42
     Those
    -1.42
    POSITIVE LOGITS
     ebbe
    1.61
     that
    1.55
     endlich
    1.52
    ി
    1.47
    taja
    1.45
    edos
    1.44
    釔
    1.44
    |
    1.42
    frica
    1.41
     ど
    1.41
    Activations Density 0.009%

    No Known Activations