© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 9-GEMMASCOPE-2-RES-262K
    7. 11600
    Prev
    Next
    INDEX
    Explanations

    reading, explaining, becoming

    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
    withstanding
    1.44
    atious
    1.42
    ಡೆ
    1.41
    ان
    1.40
     PTI
    1.38
    ğunu
    1.35
     marque
    1.35
    <0x96>
    1.35
     joka
    1.34
    <unused2194>
    1.33
    POSITIVE LOGITS
    i
    1.44
    {-\
    1.35
    ter
    1.34
     abound
    1.32
    ഭ
    1.32
     pořád
    1.32
    ди
    1.31
    endium
    1.29
    특별시
    1.28
    біль
    1.27
    Activations Density 0.000%

    No Known Activations