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. 9-GEMMASCOPE-2-RES-262K
    4. 7399
    Prev
    Next
    INDEX
    Explanations

    price of

    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_9_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
    ន៍
    2.53
    о
    2.35
    将
    2.34
     erythematosus
    2.31
    lar
    2.30
    お
    2.28
    zoeken
    2.22
    methylation
    2.19
    стью
    2.17
    lo
    2.14
    POSITIVE LOGITS
    an
    3.11
     trị
    2.37
    			
    2.19
    ς
    2.11
    anath
    2.11
    ের
    2.10
    но
    2.06
    ০
    2.04
    schnitt
    2.03
    もの
    2.01
    Activations Density 0.377%

    No Known Activations