© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 14157
    Prev
    Next
    INDEX
    Explanations

    ```xml <svg

    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
    زاد
    1.68
    প্তাহ
    1.68
    وام
    1.47
    вра
    1.46
     ठ
    1.42
    <bos>
    1.41
    ۰
    1.41
    zag
    1.39
    र
    1.39
    А
    1.38
    POSITIVE LOGITS
     siège
    2.02
     praises
    1.99
     अलर्ट
    1.99
    Sorter
    1.97
     homenagem
    1.92
     Micah
    1.91
     guests
    1.91
    guests
    1.91
     serviços
    1.91
     funkcji
    1.90
    Activations Density 0.000%

    No Known Activations