© 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. 22-GEMMASCOPE-2-RES-65K
    7. 6528
    Prev
    Next
    INDEX
    Explanations

    each other

    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_22_width_65k_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
    ں
    1.32
     ogni
    1.29
     every
    1.28
    ئے
    1.27
    σο
    1.24
     Ogni
    1.23
    every
    1.21
    挲
    1.21
    кси
    1.19
    EVERY
    1.18
    POSITIVE LOGITS
    ل
    1.66
     successive
    1.47
     respective
    1.37
     jų
    1.33
    กรรม
    1.32
    ie
    1.32
     dintre
    1.28
    기
    1.28
     of
    1.28
    स
    1.25
    Activations Density 0.068%

    No Known Activations