© 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. 46334
    Prev
    Next
    INDEX
    Explanations

    promoters, partnership, blog, honest, rats, merritt

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

    Chinese and foreign language keywords

    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
     substant
    0.46
     gras
    0.45
     OPD
    0.45
     prosp
    0.44
     nop
    0.44
    a
    0.43
     Transvaal
    0.43
    हारा
    0.42
     currentDate
    0.42
     Rash
    0.42
    POSITIVE LOGITS
    ボリューム
    0.48
    最大
    0.47
    ('.',
    0.45
    cular
    0.45
    サイズ
    0.44
    中国
    0.44
    る
    0.44
     শরীরের
    0.44
    手続き
    0.43
    ｌ
    0.43
    Activations Density 0.000%

    No Known Activations