© 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. 13-GEMMASCOPE-2-RES-16K
    7. 843
    Prev
    Next
    INDEX
    Explanations

    contextual explanations

    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
    ؛
    1.21
    >();
    1.21
    Dimension
    1.21
    innam
    1.20
     ومش
    1.20
    MARKED
    1.18
    麼
    1.17
    ަރު
    1.16
    huang
    1.14
    ;
    1.13
    POSITIVE LOGITS
     meantime
    1.73
    此同时
    1.68
    另一方面
    1.53
    与此同时
    1.49
    此外
    1.48
    除此之外
    1.48
     questo
    1.43
     recientes
    1.41
     apesar
    1.40
     niektórych
    1.37
    Activations Density 1.709%

    No Known Activations