© 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-16K
    7. 2465
    Prev
    Next
    INDEX
    Explanations

    breaking down and explaining

    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_16k_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
    !,
    1.40
    *,
    1.37
    ,/
    1.36
    /,
    1.36
    ,
    1.33
    **,
    1.31
    ,*
    1.30
    ™,
    1.26
    ，
    1.26
    ;,
    1.26
    POSITIVE LOGITS
    はその
    0.79
    الغ
    0.79
     لم
    0.78
     minden
    0.78
     لا
    0.78
     હ
    0.75
    꽤
    0.73
     گیا۔
    0.73
     ك
    0.71
     પ્ર
    0.71
    Activations Density 0.155%

    No Known Activations