© 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-3-1B-IT
    5. 13-GEMMASCOPE-2-RES-65K
    7. 1443
    Prev
    Next
    INDEX
    Explanations

    __(csv

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-it/resid_post/layer_13_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
     change
    0.75
    "
    0.69
    change
    0.68
     perfect
    0.66
    making
    0.62
     seeming
    0.62
    ers
    0.62
     so
    0.61
     conviction
    0.59
     most
    0.57
    POSITIVE LOGITS
     هي
    1.39
     كان
    1.29
     ي
    1.28
     إلى
    1.23
     على
    1.21
     mengakses
    1.19
     обеспечивает
    1.19
     مدير
    1.16
     위한
    1.16
     находится
    1.16
    Activations Density 0.002%

    No Known Activations