© 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-3-1B-IT
    5. 22-GEMMASCOPE-2-RES-16K
    7. 782
    Prev
    Next
    INDEX
    Explanations

    siri Satsuki

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-it/resid_post/layer_22_width_16k_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
    睹
    0.59
    மாத
    0.58
    iciones
    0.58
    মায়
    0.56
    FrameworkElement
    0.55
    naissance
    0.54
    veys
    0.54
    teborg
    0.54
     माध
    0.53
    铉
    0.53
    POSITIVE LOGITS
     Works
    0.60
     ഷ
    0.60
     Share
    0.60
     Pic
    0.58
     WORKS
    0.57
     works
    0.57
     Al
    0.57
     Sharing
    0.57
     sharing
    0.56
     Cast
    0.55
    Activations Density 1.044%

    No Known Activations