© 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. 6901
    Prev
    Next
    INDEX
    Explanations

    code block delimiters and include statements

    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
     kalla
    -0.85
     cort
    -0.79
    camel
    -0.77
     tane
    -0.77
     Talla
    -0.75
     shaving
    -0.75
     masih
    -0.73
    ʳ
    -0.73
    ähteet
    -0.73
     whofe
    -0.73
    POSITIVE LOGITS
     hence
    0.83
     propietarios
    0.83
     humanidad
    0.82
    Marin
    0.81
    berti
    0.74
     Trigon
    0.73
    VERBOSE
    0.73
    ocimiento
    0.72
     Microbial
    0.72
    lipo
    0.72
    Activations Density 0.000%

    No Known Activations