© 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. 7-GEMMASCOPE-2-RES-16K
    7. 11294
    Prev
    Next
    INDEX
    Explanations

    given a task description

    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_7_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
    ing
    4.73
    고
    4.00
    า
    3.94
    ೆ
    3.90
    ت
    3.82
    ي
    3.69
    ン
    3.59
    ி
    3.47
    ი
    3.46
    ה
    3.32
    POSITIVE LOGITS
    de
    3.37
    𝗱
    3.08
    𝗴
    3.03
    𝘀
    2.88
    ۷
    2.82
    ۸
    2.72
    𝗹
    2.70
    GRect
    2.68
    ۶
    2.67
    gle
    2.67
    Activations Density 0.044%

    No Known Activations