© 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. 203742
    Prev
    Next
    INDEX
    Explanations

    final four

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

    sets, groups, validate, gamers, motivation

    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
    在这
    0.50
    䡈
    0.49
     собра
    0.45
    柟
    0.45
    䪱
    0.45
     একখানি
    0.44
    现场
    0.44
     лабора
    0.43
    рия
    0.43
    মধ্যে
    0.42
    POSITIVE LOGITS
    ri
    0.65
    ul
    0.57
    ne
    0.56
    fool
    0.54
    rets
    0.53
    gu
    0.53
    a
    0.52
    o
    0.52
    em
    0.51
    yue
    0.49
    Activations Density 0.000%

    No Known Activations