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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-4B-IT
    3. 17-GEMMASCOPE-2-RES-65K
    4. 1928
    Prev
    Next
    INDEX
    Explanations

    numerical sequences

    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
    0.74
    o
    0.71
    i
    0.71
    Hz
    0.68
     moyen
    0.68
     Horizon
    0.67
    BR
    0.67
     Certains
    0.65
    grounds
    0.65
    교
    0.65
    POSITIVE LOGITS
    inephrine
    0.78
     Arzneim
    0.78
     치료
    0.78
    اتھن
    0.75
    iovascular
    0.74
    imantan
    0.73
     наука
    0.72
     здоровья
    0.72
    过去了
    0.72
     amounted
    0.72
    Activations Density 0.051%

    No Known Activations