© 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. 34-GEMMASCOPE-RES-131K
    7. 63406
    Prev
    Next
    INDEX
    Explanations

    wearing clothes or apparel

    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
    括
    -0.84
    lación
    -0.73
     cation
    -0.73
     Grom
    -0.73
     Peterson
    -0.71
    kháu
    -0.71
    ytu
    -0.71
    calculate
    -0.71
    enste
    -0.70
    velope
    -0.70
    POSITIVE LOGITS
     wearing
    6.25
     wear
    5.31
     wore
    4.84
    Wearing
    4.75
     wears
    4.56
     Wearing
    4.56
    wearing
    4.56
    Wear
    3.84
     Wear
    3.73
    wear
    3.53
    Activations Density 0.108%

    No Known Activations