© 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. 40-GEMMASCOPE-2-RES-16K
    7. 8229
    Prev
    Next
    INDEX
    Explanations

    writing process, listening, speaking

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

    grammar and grammar correction

    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_40_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     mù
    0.43
     тексто
    0.41
     Analyze
    0.39
    ometrical
    0.39
     Kew
    0.38
     OCR
    0.38
    テキスト
    0.38
     الترب
    0.37
    뮈
    0.37
     Comparator
    0.37
    POSITIVE LOGITS
     escuch
    0.47
     dictated
    0.45
    ടുത്ത
    0.44
     planification
    0.44
     escucha
    0.43
     exchanges
    0.43
    家族
    0.42
     productie
    0.42
     producción
    0.42
     escuchado
    0.41
    Activations Density 0.040%

    No Known Activations