© 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. 31-GEMMASCOPE-2-RES-262K
    7. 8571
    Prev
    Next
    INDEX
    Explanations

    categories and examples

    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_31_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
    정에
    0.47
    괵
    0.45
    정이
    0.43
    
    0.43
    ्राष्ट
    0.43
    ö
    0.42
     butyl
    0.41
     cento
    0.41
    ्रा
    0.40
    ಳಿ
    0.40
    POSITIVE LOGITS
    ка
    0.50
    скольку
    0.49
     =
    0.49
     on
    0.48
     расска
    0.46
    hythm
    0.45
    ના
    0.44
     Среди
    0.44
     schlecht
    0.43
    :
    0.42
    Activations Density 0.000%

    No Known Activations