© 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. 1663
    Prev
    Next
    INDEX
    Explanations

    authors named after by

    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
    ↵↵
    0.99
    im
    0.94
    1
    0.94
    he
    0.91
    '
    0.90
     no
    0.89
    ine
    0.87
    !
    0.84
    un
    0.84
    ,
    0.84
    POSITIVE LOGITS
    竰
    1.60
    <unused227>
    1.52
     Gosudarstvennyj
    1.48
    ErrorClazz
    1.48
    Ყ
    1.47
    <unused344>
    1.46
    <unused1163>
    1.45
    <unused1223>
    1.44
    篒
    1.44
    <unused345>
    1.43
    Activations Density 0.015%

    No Known Activations