© 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. 13-GEMMASCOPE-2-RES-16K
    7. 11848
    Prev
    Next
    INDEX
    Explanations

    MongoDB

    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_13_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
    lığı
    1.83
    ılmış
    1.75
    ıp
    1.71
    lında
    1.62
    下的
    1.60
    꺅
    1.60
    জ্জিত
    1.60
    lığını
    1.57
    زیز
    1.55
    stuk
    1.54
    POSITIVE LOGITS
     Charge
    2.18
    ুখ
    1.87
    ی
    1.84
    Charge
    1.80
    ZERO
    1.78
    zeko
    1.73
    exhaust
    1.72
    Mq
    1.71
     superpowers
    1.71
    iou
    1.71
    Activations Density 0.003%

    No Known Activations