© 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
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 13220
    Prev
    Next
    INDEX
    Explanations

    private member 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_22/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
     célè
    -2.17
     rése
    -2.09
    鳚
    -2.03
     kabát
    -1.97
     régal
    -1.95
     insiste
    -1.95
    offered
    -1.91
     suscit
    -1.89
     bénéficiaire
    -1.88
     écl
    -1.86
    POSITIVE LOGITS
     generally
    1.95
     very
    1.88
     to
    1.85
     in
    1.81
     now
    1.81
     often
    1.80
     also
    1.77
     more
    1.76
     actually
    1.73
     most
    1.69
    Activations Density 0.005%

    No Known Activations