© 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. 142831
    Prev
    Next
    INDEX
    Explanations

    inspection of

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

    breakdown of concepts

    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
    uns
    0.47
    tel
    0.47
    tarea
    0.46
    手
    0.46
     estava
    0.44
    tain
    0.44
     stains
    0.44
    '
    0.44
    holders
    0.44
    king
    0.43
    POSITIVE LOGITS
     এইসব
    0.46
    смотреть
    0.44
    нік
    0.44
     dokładnie
    0.43
    が存在
    0.42
     ভোর
    0.42
     Diagnose
    0.42
     політи
    0.41
     усі
    0.41
     découvrir
    0.40
    Activations Density 0.000%

    No Known Activations