© 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. 123770
    Prev
    Next
    INDEX
    Explanations

    getting started, access, organize

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

    metadata, AUC, undefined

    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
    ας
    0.48
    ậc
    0.48
     carpentry
    0.47
     carpenter
    0.47
    ục
    0.45
    তরাং
    0.45
     watertight
    0.44
     Vascular
    0.44
     ب
    0.43
     στους
    0.43
    POSITIVE LOGITS
    的時間
    0.49
    ត្រូ
    0.49
    för
    0.48
    decoder
    0.47
    dete
    0.47
    nuevo
    0.47
    helping
    0.46
     データ
    0.46
    demos
    0.46
     anuncio
    0.45
    Activations Density 0.001%

    No Known Activations