© 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. 85426
    Prev
    Next
    INDEX
    Explanations

    embodiments of

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

    potential consequences or approaches

    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
    Reducing
    0.46
    Trend
    0.46
     Trend
    0.45
    ')));
    0.44
     お
    0.43
    olate
    0.43
    reducing
    0.42
    =',
    0.42
     及
    0.42
     通
    0.42
    POSITIVE LOGITS
     multit
    0.48
     rupani
    0.47
    ǎng
    0.46
     malade
    0.46
     mixto
    0.46
    omét
    0.44
    சிவ
    0.44
    㖣
    0.44
     handic
    0.44
     taxonom
    0.43
    Activations Density 0.000%

    No Known Activations