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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 732
    Prev
    Next
    INDEX
    Explanations

    boost morale and spirits

    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
     offrant
    -1.42
     spéciaux
    -1.34
     gräns
    -1.32
    рису
    -1.31
     perpé
    -1.31
     REALLY
    -1.31
     organisé
    -1.30
     gonzález
    -1.30
     présentée
    -1.30
    为什么
    -1.30
    POSITIVE LOGITS
     as
    1.85
     on
    1.79
     confidence
    1.77
     during
    1.57
     before
    1.50
     in
    1.42
     while
    1.34
     morale
    1.31
     espectacular
    1.30
     although
    1.27
    Activations Density 0.034%

    No Known Activations