© 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. 7-GEMMASCOPE-2-RES-16K
    7. 12713
    Prev
    Next
    INDEX
    Explanations

    cooperative games

    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
    ｅ
    2.73
    ifying
    2.57
    ডস
    2.41
    ‌ನ
    2.38
    ামুটি
    2.38
    መሳሳይ
    2.37
    カテゴリ
    2.36
    glied
    2.35
    𝐞
    2.35
    𝙮
    2.34
    POSITIVE LOGITS
    ch
    2.61
    ynd
    2.54
    yses
    2.39
    elev
    2.37
    ലേ
    2.36
    ey
    2.32
    ei
    2.32
    เอียด
    2.28
    AntiForgeryToken
    2.21
    $.\
    2.20
    Activations Density 0.003%

    No Known Activations