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. 7410
    Prev
    Next
    INDEX
    Explanations

    new products, services, and ideas

    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
    ००
    2.23
    ১
    2.16
    ্টি
    2.12
    ниях
    2.07
    ﮩ
    2.04
    ‍♀️
    2.03
     remission
    2.03
    л
    2.02
    琶
    2.01
    认
    2.01
    POSITIVE LOGITS
    spapers
    3.38
     zealand
    3.03
    foundland
    2.84
    comers
    2.67
     सिरे
    2.67
    ви
    2.60
     york
    2.59
    found
    2.53
     minted
    2.50
     नवे
    2.44
    Activations Density 0.201%

    No Known Activations