© 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. 5232
    Prev
    Next
    INDEX
    Explanations

    Go web server code

    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
    V
    1.31
    OR
    1.24
    Z
    1.14
    G
    1.13
    U
    1.13
    IS
    1.12
    IN
    1.11
    AL
    1.07
    OM
    1.06
    OP
    1.06
    POSITIVE LOGITS
     doenças
    1.53
     adulthood
    1.35
     wildfires
    1.32
     consequências
    1.32
     adolescents
    1.31
     crianças
    1.31
     século
    1.27
     adoles
    1.27
     tokamaks
    1.26
     hemicontinuous
    1.26
    Activations Density 0.000%

    No Known Activations