© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 74363
    Prev
    Next
    INDEX
    Explanations

    skill sets and features

    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
    ventes
    -1.68
    絰
    -1.61
     with
    -1.58
    ajemen
    -1.50
    ⸒
    -1.46
     rửa
    -1.44
     through
    -1.42
    我们
    -1.39
    minutos
    -1.37
    Hélène
    -1.35
    POSITIVE LOGITS
     serene
    1.64
    metrist
    1.63
     desires
    1.61
    唖
    1.57
    C
    1.54
     obscure
    1.52
     ensuing
    1.52
    matchCondition
    1.52
    みや
    1.52
    therners
    1.50
    Activations Density 0.009%

    No Known Activations