© 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. 204855
    Prev
    Next
    INDEX
    Explanations

    mod done

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

    casual, loose-fitting shirts

    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
    <0xE8>
    0.47
    вається
    0.45
    廾
    0.44
     sere
    0.44
    Leadership
    0.43
    럼
    0.43
    Agriculture
    0.42
    لق
    0.42
    рана
    0.42
     fuga
    0.42
    POSITIVE LOGITS
    ccak
    0.48
    峤
    0.47
    ipy
    0.44
     моделей
    0.43
    िड
    0.43
     शिवाय
    0.42
     девушки
    0.42
    เพื่อ
    0.42
    inato
    0.41
     владель
    0.41
    Activations Density 0.001%

    No Known Activations