© 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. 216016
    Prev
    Next
    INDEX
    Explanations

    reporting quarter and month

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

    close your eyes

    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
    /
    0.47
    连
    0.46
     quasi
    0.45
     archive
    0.45
     exon
    0.44
    反
    0.44
     archival
    0.43
     elim
    0.42
    "
    0.42
    \
    0.42
    POSITIVE LOGITS
    пи
    0.57
    емом
    0.55
    𝗂
    0.52
     ಮನೆಯ
    0.50
    ία
    0.50
    deload
    0.50
     प्रिपरेशन
    0.49
    фро
    0.48
    ia
    0.48
    плення
    0.48
    Activations Density 0.001%

    No Known Activations