© 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. 85820
    Prev
    Next
    INDEX
    Explanations

    medical examinations and procedures

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

    Story structure elements

    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
    นิ
    0.52
    ด
    0.50
    ตร
    0.49
    挙
    0.49
    บ
    0.47
     Handel
    0.46
    กก
    0.46
     task
    0.46
     Farb
    0.45
    นี
    0.45
    POSITIVE LOGITS
    players
    0.52
    identité
    0.47
    arrays
    0.46
     filles
    0.46
     армии
    0.46
     economía
    0.46
    <0xA9>
    0.45
     मोटर्स
    0.45
    🚍
    0.45
     pitchers
    0.44
    Activations Density 0.000%

    No Known Activations