© 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. 93206
    Prev
    Next
    INDEX
    Explanations

    titles and introductory phrases

    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
    dania
    -1.03
    Fmt
    -0.98
    いただく
    -0.95
     zodiaco
    -0.95
     tienes
    -0.95
    tien
    -0.94
    baca
    -0.93
    kiej
    -0.93
     también
    -0.92
    ité
    -0.90
    POSITIVE LOGITS
     still
    1.08
     affari
    1.05
    phenols
    1.05
     messages
    1.04
    Different
    1.04
     personalizada
    1.03
    During
    1.02
     updates
    1.01
     Beweg
    0.97
    Organisator
    0.95
    Activations Density 0.003%

    No Known Activations