© 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. 196558
    Prev
    Next
    INDEX
    Explanations

    advice and descriptions

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

    remove shoes

    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
    テキスト
    0.52
    文字
    0.51
    acad
    0.49
     лет
    0.49
    QUARE
    0.47
    备注
    0.47
    尚
    0.46
    字母
    0.46
    ケア
    0.46
    goto
    0.45
    POSITIVE LOGITS
     Erfol
    0.54
     agonists
    0.49
    ilí
    0.48
     česk
    0.47
    ilte
    0.47
     $)$
    0.44
     Aéroport
    0.44
     eaters
    0.44
    ÉE
    0.43
     incarnations
    0.43
    Activations Density 0.000%

    No Known Activations