© 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. 8449
    Prev
    Next
    INDEX
    Explanations

    clothing and style

    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
     verdaderos
    -1.41
     predominantly
    -1.34
     potenciales
    -1.33
     única
    -1.32
     ganadores
    -1.32
     fantastic
    -1.31
     kilómetros
    -1.27
     antiguos
    -1.26
    veu
    -1.25
    áneo
    -1.23
    POSITIVE LOGITS
     In
    1.45
     Chinois
    1.33
    ｽ
    1.22
     hesitation
    1.20
    👔
    1.17
     Even
    1.16
     When
    1.15
    In
    1.15
    ｪ
    1.15
    tské
    1.09
    Activations Density 0.038%

    No Known Activations