© 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. 12136
    Prev
    Next
    INDEX
    Explanations

    programming keywords and syntax

    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
    ми
    2.27
     SERIAL
    2.23
    िल
    2.17
    น์
    2.14
    pais
    2.13
     ран
    2.05
     動
    2.02
     mysteries
    1.91
     SUPER
    1.91
     RAID
    1.91
    POSITIVE LOGITS
    ihat
    2.27
    jeća
    2.13
    yemek
    2.04
    <bos>
    2.03
    تج
    1.99
    úč
    1.81
    ынша
    1.81
    yczy
    1.78
    এর
    1.76
    ämään
    1.76
    Activations Density 0.000%

    No Known Activations