© 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. 250580
    Prev
    Next
    INDEX
    Explanations

    demands, Minister, arrested

    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
     வேக
    0.49
     скорости
    0.48
    atost
    0.48
    она
    0.48
    蓯
    0.48
     всіх
    0.47
    ด
    0.47
     élytres
    0.46
    훨
    0.46
    ТО
    0.45
    POSITIVE LOGITS
     terrorism
    0.48
     विगत
    0.48
    hemer
    0.48
     an
    0.47
     sociological
    0.47
     fanatic
    0.46
    kur
    0.45
     fanatics
    0.45
     controversy
    0.44
     liquidation
    0.44
    Activations Density 0.001%

    No Known Activations