© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 9-GEMMASCOPE-2-RES-262K
    7. 9799
    Prev
    Next
    INDEX
    Explanations

    eyes, claws, paws, and hands

    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
    ً
    1.39
    ën
    1.24
    un
    1.20
    oxid
    1.18
     AKT
    1.16
    ‍♀️
    1.14
    ~/
    1.14
    vict
    1.14
    ɳ
    1.09
     lone
    1.08
    POSITIVE LOGITS
    る
    1.49
    yb
    1.32
    ت
    1.29
    ীভূত
    1.29
     tiden
    1.29
    ्स
    1.29
     ব্যতিক্রম
    1.28
    ਾ
    1.28
    此同时
    1.28
     Gebiet
    1.27
    Activations Density 0.118%

    No Known Activations