© 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. 13506
    Prev
    Next
    INDEX
    Explanations

    string name value SERVICE

    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
    規格
    -0.81
     تواند
    -0.81
    '/>
    -0.81
     request
    -0.80
     두
    -0.78
    unut
    -0.77
     minimo
    -0.76
    เพื่อ
    -0.74
    ERD
    -0.74
     الها
    -0.74
    POSITIVE LOGITS
     lexicon
    0.91
    Traduction
    0.90
     explanation
    0.89
     beside
    0.89
     labelling
    0.88
     interchangeable
    0.84
    étaro
    0.84
    TextBoxColumn
    0.84
     instead
    0.83
     each
    0.83
    Activations Density 0.022%

    No Known Activations