© 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. 13782
    Prev
    Next
    INDEX
    Explanations

    symbolic link

    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
    el
    0.91
    မူ
    0.81
    $(".
    0.77
    ward
    0.74
    ft
    0.71
    fe
    0.71
     Schritte
    0.70
    げ
    0.69
     $
    0.69
    parseInt
    0.68
    POSITIVE LOGITS
    ={
    0.91
     ={
    0.90
     જેને
    0.89
    jhelp
    0.88
     үшін
    0.88
    ◈
    0.87
    KURZBESCHREIBUNG
    0.86
    股票
    0.86
     Shabd
    0.84
    гают
    0.84
    Activations Density 0.000%

    No Known Activations