© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 194919
    Prev
    Next
    INDEX
    Explanations

    multi-lingual terms and categories

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     encarg
    0.42
     permisos
    0.42
     zaś
    0.41
     manipular
    0.40
     procéd
    0.39
     deixe
    0.38
    憚
    0.38
    жал
    0.38
     rollover
    0.37
    茷
    0.37
    POSITIVE LOGITS
    зонта
    0.44
     φορά
    0.40
     Лю
    0.39
     Кам
    0.38
    িলা
    0.37
     พิจ
    0.37
     Maser
    0.36
     Ма
    0.35
     дро
    0.35
    หุ้น
    0.35
    Activations Density 0.000%

    No Known Activations