© 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. 103084
    Prev
    Next
    INDEX
    Explanations

    From locations or origins

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

    sender information in headers

    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
     exempel
    0.44
     증
    0.44
     örne
    0.44
     bấm
    0.43
     अरे
    0.43
    證
    0.43
     spes
    0.43
     breakpoint
    0.42
     정상
    0.42
     AssertionError
    0.42
    POSITIVE LOGITS
    ม
    0.44
    skoj
    0.44
    stig
    0.44
    ک
    0.44
    andan
    0.43
    andang
    0.43
    ma
    0.42
    trails
    0.42
    significant
    0.42
    steiger
    0.42
    Activations Density 0.002%

    No Known Activations