© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 15056
    Prev
    Next
    INDEX
    Explanations

    initials like T.V

    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_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
    蛧
    -1.82
    ities
    -1.58
    焄
    -1.57
    ・・・・
    -1.55
     dazzling
    -1.55
    Significado
    -1.50
    when
    -1.49
    sobí
    -1.48
     kiedy
    -1.48
     noticeable
    -1.48
    POSITIVE LOGITS
     They
    1.80
    憷
    1.63
    piar
    1.62
     Muchas
    1.49
    {(-
    1.48
     Erkrank
    1.48
    getti
    1.48
    怏
    1.45
    xiii
    1.44
     frontières
    1.44
    Activations Density 0.050%

    No Known Activations