© 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. 246439
    Prev
    Next
    INDEX
    Explanations

    Hong Kong

    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
    ᙱ
    0.67
    银行
    0.54
    베이스
    0.47
    ﻐ
    0.47
    ப்பிய
    0.47
    تباينه
    0.47
    ೆಂದು
    0.47
    grocery
    0.46
    个人的
    0.46
    𒉡
    0.45
    POSITIVE LOGITS
    .
    0.54
    uru
    0.53
    ilah
    0.52
    ur
    0.51
    ere
    0.50
    erset
    0.50
    uld
    0.49
    org
    0.47
    avier
    0.47
    au
    0.47
    Activations Density 0.000%

    No Known Activations