© 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. 167735
    Prev
    Next
    INDEX
    Explanations

    huge flying elements demanded

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

    non-english or specific terms

    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
     exert
    0.49
     that
    0.48
     briefly
    0.48
     classify
    0.47
     instantly
    0.47
    ヘ
    0.47
     sağ
    0.47
     ACHIE
    0.46
    ;"
    0.46
    ;
    0.46
    POSITIVE LOGITS
    क्रिया
    0.48
    aprend
    0.45
    árl
    0.44
    ojana
    0.44
    átky
    0.44
    yloxy
    0.43
    rapa
    0.43
     Programs
    0.42
     Tribut
    0.42
     Partly
    0.42
    Activations Density 0.000%

    No Known Activations