© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 68034
    Prev
    Next
    INDEX
    Explanations

    dress up and dress code

    np_acts-logits-general · gemini-2.5-flash-lite

    dressing/dress

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    .
    0.81
     gehören
    0.70
    BA
    0.67
    ]
    0.66
    }
    0.59
    the
    0.59
    )
    0.58
    {
    0.58
    [
    0.58
    CL
    0.57
    POSITIVE LOGITS
     bicovariant
    0.67
    ш
    0.66
    ubarb
    0.65
    inan
    0.61
    CriteriaUtils
    0.61
    尼亚克
    0.61
    腓
    0.61
    ियस
    0.60
    ुलिस
    0.60
    opathological
    0.60
    Activations Density 0.039%

    No Known Activations