© 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. 193034
    Prev
    Next
    INDEX
    Explanations

    charts, generally, place, much, All, ABS, studied

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

    topics and actions

    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
     아름
    0.53
     mooie
    0.50
     コンパクト
    0.49
     計
    0.49
     chaud
    0.48
     mooi
    0.48
     woodworking
    0.47
     boiling
    0.46
     discernible
    0.46
     woodpe
    0.46
    POSITIVE LOGITS
    ب
    0.64
    لو
    0.51
    6
    0.48
    ي
    0.48
    Jim
    0.47
    NOR
    0.47
    جل
    0.47
    9
    0.46
    Vậy
    0.46
    نس
    0.45
    Activations Density 0.001%

    No Known Activations