© 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. 2491
    Prev
    Next
    INDEX
    Explanations

    portion of

    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
    آمد
    2.13
    stellungen
    2.05
    <bos>
    2.02
     zwią
    2.00
    یاط
    1.95
    דר
    1.90
    wijs
    1.90
    ښ
    1.89
    숭
    1.88
    ährt
    1.86
    POSITIVE LOGITS
    ViewGroup
    1.91
    operating
    1.86
     доходов
    1.79
    बॉलीवुड
    1.78
    income
    1.75
    idão
    1.73
    lywood
    1.70
    function
    1.66
    edly
    1.66
    heartedly
    1.64
    Activations Density 0.325%

    No Known Activations