© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 166591
    Prev
    Next
    INDEX
    Explanations

    time, family, and comparison

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

    framing of issues

    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
    Negative Logits
    㳡
    0.56
    ריק
    0.55
    евского
    0.51
    рик
    0.50
     mercure
    0.49
    рур
    0.49
    隶
    0.49
    дели
    0.49
    σία
    0.49
    աշ
    0.48
    POSITIVE LOGITS
    nst
    0.62
    te
    0.52
    un
    0.50
    se
    0.49
    s
    0.49
    og
    0.48
    ns
    0.48
    ge
    0.46
    as
    0.46
    nd
    0.46
    Activations Density 0.001%

    No Known Activations