© 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. 17-GEMMASCOPE-2-RES-16K
    7. 1144
    Prev
    Next
    INDEX
    Explanations

    therapy, breach, buddies, injuries, premiums

    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_16k_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
     procéder
    1.06
    ფილი
    1.00
     kunna
    0.97
     불구하고
    0.96
    도
    0.96
    在于
    0.95
    corollary
    0.95
    대학교
    0.94
    şik
    0.93
    이라
    0.92
    POSITIVE LOGITS
    ات
    1.27
    ations
    1.18
    ы
    1.12
    ancies
    1.12
    s
    1.11
     or
    1.11
    ers
    1.10
    ets
    1.09
    們
    1.09
     certifications
    1.08
    Activations Density 0.259%

    No Known Activations