© 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. 22-GEMMASCOPE-2-RES-262K
    7. 4303
    Prev
    Next
    INDEX
    Explanations

    action of sitting

    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_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
    Spending
    0.97
    াণী
    0.95
    ي
    0.95
     الأس
    0.90
     św
    0.90
    Fed
    0.89
    ت
    0.89
     인해
    0.88
    Books
    0.87
     kDa
    0.87
    POSITIVE LOGITS
    URDAY
    1.33
     vremena
    1.26
    rapy
    1.24
     amet
    1.21
     MongoClient
    1.19
     atop
    1.18
    UARY
    1.16
    chel
    1.13
     comedor
    1.10
     expectant
    1.07
    Activations Density 0.059%

    No Known Activations