© 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. 34-GEMMASCOPE-RES-131K
    7. 76579
    Prev
    Next
    INDEX
    Explanations

    code delimiters and identifiers

    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_34/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
     тяжело
    -0.68
     Bingham
    -0.64
    litt
    -0.64
    agua
    -0.64
    modelos
    -0.62
    紧
    -0.60
    Infinity
    -0.60
     baseUrl
    -0.60
    Quit
    -0.60
     ters
    -0.60
    POSITIVE LOGITS
    ktop
    0.69
     caramelo
    0.65
    fting
    0.65
     cumpleaños
    0.65
    слі
    0.65
    adder
    0.65
     deposits
    0.64
    curo
    0.63
    posta
    0.63
     Vara
    0.63
    Activations Density 0.077%

    No Known Activations