© 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-3-4B-IT
    5. 22-GEMMASCOPE-2-RES-262K
    7. 7438
    Prev
    Next
    INDEX
    Explanations

    example usage code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_22_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
     preprocessing
    0.80
     XGB
    0.78
     له‌
    0.77
    𠃌
    0.72
     Processing
    0.69
     Extraction
    0.69
     DPI
    0.68
     UIF
    0.68
     preprocess
    0.67
     Appendix
    0.67
    POSITIVE LOGITS
    if
    0.81
    animals
    0.71
    rept
    0.69
    ################
    0.69
    #
    0.69
    say
    0.68
    print
    0.67
    chocolate
    0.67
    animal
    0.67
    celebr
    0.67
    Activations Density 0.075%

    No Known Activations