© 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. 5409
    Prev
    Next
    INDEX
    Explanations

    variables followed by inline code formatting

    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
    y
    1.28
    m
    1.11
    in
    1.11
    l
    1.07
    r
    1.05
    a
    1.01
    u
    1.00
    ل
    0.95
    n
    0.94
    er
    0.94
    POSITIVE LOGITS
    idding
    0.68
    Какой
    0.66
    ourse
    0.64
    ussels
    0.62
    arganya
    0.62
    ould
    0.61
    enean
    0.61
    हमारे
    0.61
    ೈ
    0.61
    Какие
    0.60
    Activations Density 0.435%

    No Known Activations