© 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. 118058
    Prev
    Next
    INDEX
    Explanations

    endorsed by

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

    legal or official contexts

    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
     sasane
    0.50
    uq
    0.49
    aeskeygenassist
    0.48
     telescop
    0.48
    ページ
    0.48
    teles
    0.47
     veilig
    0.46
     intermin
    0.46
     صفحه
    0.46
    )&=
    0.45
    POSITIVE LOGITS
     Canterbury
    0.49
    Tum
    0.47
    టో
    0.46
     Rinse
    0.45
     Ravenna
    0.45
    ECTOR
    0.45
     Poker
    0.44
     of
    0.44
     Rage
    0.44
     Paren
    0.44
    Activations Density 0.000%

    No Known Activations