© 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. 206013
    Prev
    Next
    INDEX
    Explanations

    vehicles

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

    Strengths, Radley, Blitzkrieg

    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
    Not in Any Lists

    No Comments

    Negative Logits
    猎
    0.43
    ิก
    0.41
    ช่วย
    0.40
    ลิ
    0.40
    ');
    0.40
    เซ
    0.40
     et
    0.39
    相当
    0.38
    资金
    0.38
     Airways
    0.38
    POSITIVE LOGITS
     માતા
    0.54
     ಮಹಿ
    0.53
     clás
    0.53
    blusas
    0.52
     familiarize
    0.52
    hiv
    0.51
    蠣
    0.50
    MODKEY
    0.50
    ங்கில
    0.49
    bnf
    0.49
    Activations Density 0.001%

    No Known Activations