© 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. 13676
    Prev
    Next
    INDEX
    Explanations

    original and variations

    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
    𝖔
    0.86
     Basics
    0.82
    स्टल
    0.81
    orm
    0.79
    ډ
    0.78
    acus
    0.78
    ucu
    0.77
    spots
    0.76
     σου
    0.76
    ċ
    0.75
    POSITIVE LOGITS
     original
    1.07
     originality
    0.95
    y
    0.94
     orijinal
    0.94
     oryginal
    0.94
     originales
    0.92
     ориги
    0.92
     ORIGINAL
    0.91
    ity
    0.91
    原文
    0.90
    Activations Density 0.001%

    No Known Activations