© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 22-GEMMASCOPE-2-RES-16K
    7. 8295
    Prev
    Next
    INDEX
    Explanations

    combines

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_22_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Пи
    1.13
     kr
    1.03
     ق
    1.03
     ك
    1.01
     Ру
    0.98
     ди
    0.98
     د
    0.95
    Пи
    0.91
     ب
    0.91
     Ве
    0.91
    POSITIVE LOGITS
    호를
    1.09
    원이
    0.95
    호
    0.95
    号
    0.94
    日から
    0.94
    話を
    0.93
    शोध
    0.93
    일
    0.90
    రే
    0.90
    일부터
    0.89
    Activations Density 0.022%

    No Known Activations