© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 22-GEMMASCOPE-2-RES-65K
    7. 6952
    Prev
    Next
    INDEX
    Explanations

    static code definitions

    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_65k_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
    à
    0.85
    receipt
    0.81
    delicious
    0.79
    using
    0.78
     worthwhile
    0.77
    ♐
    0.77
    driver
    0.77
     favorably
    0.76
    collection
    0.76
    pagination
    0.75
    POSITIVE LOGITS
     Caucasian
    0.71
    禹
    0.71
     Learn
    0.71
     Learning
    0.69
     Instructional
    0.69
     Hanging
    0.67
     Constit
    0.66
     Refer
    0.66
     영국
    0.66
    谘
    0.65
    Activations Density 0.002%

    No Known Activations