© 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. 102912
    Prev
    Next
    INDEX
    Explanations

    occupational safety and health issues

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

    avoiding conflict

    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
    тори
    0.45
     வண்ணப்பூ
    0.43
    нын
    0.43
     мили
    0.42
     м
    0.41
    сма
    0.41
     সৈন্যরা
    0.41
    タリ
    0.41
     Кре
    0.40
    摒
    0.40
    POSITIVE LOGITS
     encuesta
    0.59
     Prueba
    0.47
    এসসি
    0.45
     musculoskeletal
    0.45
     espectacular
    0.45
    গকে
    0.44
     Construct
    0.44
     Wins
    0.44
    prueba
    0.44
     آش
    0.43
    Activations Density 0.001%

    No Known Activations