© 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. 91053
    Prev
    Next
    INDEX
    Explanations

    sunburst guitar

    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
     ತ
    -1.02
     leiding
    -1.00
    orail
    -0.94
    othermic
    -0.85
     السياس
    -0.84
    municipio
    -0.84
     éner
    -0.83
    фильм
    -0.82
     FILMS
    -0.81
    tetrahydro
    -0.81
    POSITIVE LOGITS
     guitar
    2.02
     guitars
    1.85
     Guitar
    1.64
     Fender
    1.53
    Guitar
    1.50
    Fender
    1.47
    guitar
    1.41
     instrument
    1.38
     gitar
    1.38
     Guitars
    1.38
    Activations Density 0.031%

    No Known Activations