© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 135547
    Prev
    Next
    INDEX
    Explanations

    clothing and accessories

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

    clothing and appearance descriptions

    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
    Not in Any Lists

    No Comments

    Negative Logits
     drastically
    0.47
    į
    0.47
    ীবন
    0.46
    дії
    0.45
     muerte
    0.45
    がき
    0.45
     ответ
    0.45
    சென்னை
    0.45
    ܢܐ
    0.45
     vacío
    0.44
    POSITIVE LOGITS
     actresses
    0.49
     garlands
    0.47
     garments
    0.44
     femmes
    0.42
     vestidos
    0.42
    👘
    0.42
    βα
    0.41
     trousers
    0.40
     armored
    0.40
    👯
    0.39
    Activations Density 0.000%

    No Known Activations