© 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. 9-GEMMASCOPE-2-RES-262K
    7. 8452
    Prev
    Next
    INDEX
    Explanations

    activity and transactions

    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
    ل
    1.33
    ot
    1.22
     tireless
    1.22
     već
    1.18
    ל
    1.16
    ನೆಯ
    1.16
     bred
    1.13
    ި
    1.12
    妤
    1.10
    વિ
    1.09
    POSITIVE LOGITS
    sortie
    1.14
    #[
    1.14
    ळ्यात
    1.12
     COMPOUNDS
    1.11
    getAttribute
    1.11
    eer
    1.10
    ق
    1.10
    к
    1.09
     oxidase
    1.09
    wiście
    1.07
    Activations Density 0.174%

    No Known Activations