© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 127191
    Prev
    Next
    INDEX
    Explanations

    percentages followed by of

    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
     as
    -2.44
     with
    -1.86
     without
    -1.69
     again
    -1.66
     also
    -1.66
     several
    -1.64
     both
    -1.60
     any
    -1.55
     kurzen
    -1.54
     dovol
    -1.52
    POSITIVE LOGITS
     of
    1.82
    삵
    1.72
     ravi
    1.70
    </h3>
    1.70
     farine
    1.67
     butterknife
    1.59
     usine
    1.55
     perche
    1.54
    なんか
    1.50
     soldat
    1.48
    Activations Density 0.049%

    No Known Activations