© 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. 133164
    Prev
    Next
    INDEX
    Explanations

    change, update, new

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

    disturbed mindset, desperate plea

    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
    isant
    0.46
     돌
    0.46
     сим
    0.45
     ብዙውን
    0.45
    osulf
    0.45
     ремон
    0.44
     изо
    0.43
     다
    0.43
     establishes
    0.43
     陳
    0.43
    POSITIVE LOGITS
    لی
    0.53
    年至
    0.53
    摯
    0.52
    मा
    0.50
    را
    0.50
    У
    0.48
    ری
    0.45
    خلص
    0.45
    राइ
    0.44
    Й
    0.44
    Activations Density 0.001%

    No Known Activations