© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 22-GEMMASCOPE-2-RES-262K
    7. 2626
    Prev
    Next
    INDEX
    Explanations

    code, typescript, javascript

    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
     роках
    0.69
    姣
    0.61
     ہتھیار
    0.59
     appreciably
    0.57
     #{@
    0.57
    㑬
    0.57
     نړ
    0.56
    <0x00>
    0.56
    uncle
    0.56
    biggl
    0.55
    POSITIVE LOGITS
    कारी
    0.71
     composite
    0.70
    স্যা
    0.69
    Islamic
    0.68
    まる
    0.67
     اسرائیلی
    0.67
    פס
    0.66
    流水
    0.66
     statutory
    0.66
    太
    0.66
    Activations Density 0.049%

    No Known Activations