Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-4B-IT
    3. 17-GEMMASCOPE-2-RES-65K
    4. 1613
    Prev
    Next
    INDEX
    Explanations

    programming keywords and parameters

    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_17_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
     a
    0.91
     the
    0.86
     three
    0.83
     Boeing
    0.80
     various
    0.79
     numerous
    0.79
     more
    0.79
     IBM
    0.78
     our
    0.78
     several
    0.77
    POSITIVE LOGITS
    ها
    0.79
    ())
    0.78
    ність
    0.72
    ﺘ
    0.71
    িগ্ন
    0.71
    ()[
    0.70
    цію
    0.70
    Interested
    0.69
    ().
    0.69
    िल्‍
    0.67
    Activations Density 0.268%

    No Known Activations