© 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. 152883
    Prev
    Next
    INDEX
    Explanations

    comparisons and entities

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

    favourite pen

    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
     flared
    0.51
     Vie
    0.50
    Vie
    0.48
    resco
    0.45
    Ⴝ
    0.45
     switched
    0.44
     सबकी
    0.43
     stacked
    0.42
     raced
    0.42
     Zam
    0.42
    POSITIVE LOGITS
    に
    0.50
     vů
    0.49
    ごはん
    0.49
    으로
    0.48
    لي
    0.47
     équipe
    0.47
    이미
    0.45
    ね
    0.45
    中に
    0.45
    が
    0.45
    Activations Density 0.000%

    No Known Activations