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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-65K
    7. 739
    Prev
    Next
    INDEX
    Explanations

    open weights

    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_65k_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
     Castello
    0.38
     Giro
    0.35
    뱃
    0.33
     democrat
    0.33
    ಿಕೆಯ
    0.33
    arga
    0.33
     Long
    0.32
     carpenters
    0.32
    ɗ
    0.32
     fisheries
    0.31
    POSITIVE LOGITS
    ៦
    0.44
     соци
    0.40
    ۶
    0.40
     छह
    0.40
    ６
    0.39
     ६
    0.38
    rath
    0.38
    多
    0.38
     миллионов
    0.38
    ৬
    0.38
    Activations Density 0.041%

    No Known Activations