© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 10000
    Prev
    Next
    INDEX
    Explanations

    efficient operations

    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
    <bos>
    2.33
    ung
    1.91
    ಿಂದ
    1.83
    ிரி
    1.83
    ch
    1.83
    ưa
    1.80
    ameleon
    1.79
    isSelected
    1.76
    atat
    1.75
    ussen
    1.74
    POSITIVE LOGITS
    дьми
    2.79
    म
    2.77
     द्रविड़
    2.67
    رت
    2.63
    াতি
    2.57
    mity
    2.56
    гы
    2.50
     особо
    2.49
     इनवर्स
    2.35
    说了
    2.29
    Activations Density 0.321%

    No Known Activations