© 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. 102056
    Prev
    Next
    INDEX
    Explanations

    punctuation and instructions

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

    comparisons and 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
    ب
    0.57
    হ
    0.53
    合わせて
    0.52
    バ
    0.51
    彩
    0.50
    期
    0.50
    子
    0.49
    中
    0.49
     automate
    0.49
    早
    0.48
    POSITIVE LOGITS
    il
    0.54
    ada
    0.53
    hedron
    0.52
    en
    0.50
    et
    0.50
    uet
    0.50
    olc
    0.50
    ida
    0.50
    ill
    0.49
    rier
    0.49
    Activations Density 0.001%

    No Known Activations