© 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. 39467
    Prev
    Next
    INDEX
    Explanations

    numbers and abbreviations

    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
     breaking
    -0.85
    olon
    -0.82
    巂
    -0.81
    Nyc
    -0.80
    ENES
    -0.80
     voulais
    -0.79
     suí
    -0.79
     desmotiv
    -0.79
    زارش
    -0.79
    anging
    -0.79
    POSITIVE LOGITS
    part
    0.83
    Có
    0.82
    Mutation
    0.82
    ။
    0.79
    useNewUrlParser
    0.79
     of
    0.76
     part
    0.75
    Н
    0.75
    
    0.75
    ྱི་
    0.73
    Activations Density 0.033%

    No Known Activations