© 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. 10-GEMMASCOPE-RES-131K
    7. 12096
    Prev
    Next
    INDEX
    Explanations

    export const comment. by

    np_acts-logits-general · gemini-2.5-flash-lite

    whitespace or line breaks in code and structured text documents.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     modalidad
    -1.70
    řízen
    -1.64
     then
    -1.55
    SBATCH
    -1.52
     nación
    -1.52
     graduación
    -1.45
     nacionalidad
    -1.45
    eſ
    -1.43
     antigüedad
    -1.43
     garantía
    -1.42
    POSITIVE LOGITS
     the
    2.16
     what
    1.58
    all
    1.58
    new
    1.54
    no
    1.50
     What
    1.48
    l
    1.43
    what
    1.41
     How
    1.39
    t
    1.39
    Activations Density 0.005%

    No Known Activations