© 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. 10956
    Prev
    Next
    INDEX
    Explanations

    customizable

    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
    ing
    2.76
    ت
    2.48
    تان
    2.43
    na
    2.42
    ంది
    2.35
    alte
    2.29
    חות
    2.27
    uvwxyz
    2.26
    ิต
    2.24
    indungi
    2.21
    POSITIVE LOGITS
     aDecoder
    2.73
    ﺭ
    2.67
    ﺟ
    2.56
    œur
    2.46
    न्द्रीय
    2.46
    ேசு
    2.43
    ደም
    2.39
    econ
    2.39
    <unused2109>
    2.36
     snippets
    2.35
    Activations Density 0.180%

    No Known Activations