© 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. 6619
    Prev
    Next
    INDEX
    Explanations

    action or trend

    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
    ಂಕ
    1.67
     カスタ
    1.65
    ɰ
    1.61
     kunna
    1.60
    ེད་
    1.60
    ⁂
    1.58
    ɳ
    1.58
    Decorative
    1.58
     शकत
    1.56
    ရှင်း
    1.56
    POSITIVE LOGITS
    اته
    1.33
    坛
    1.29
    วา
    1.29
    世界的
    1.16
    FileVersion
    1.15
     Cone
    1.14
    اتها
    1.12
     world
    1.12
    ního
    1.10
    水の
    1.10
    Activations Density 0.000%

    No Known Activations