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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 1403
    Prev
    Next
    INDEX
    Explanations

    award categoriesbinary answersdays

    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
    DOMstrings
    2.92
    <unused840>
    2.80
    <unused885>
    2.73
    <unused843>
    2.72
    <unused883>
    2.70
    localVarHTTP
    2.68
    popupIsOpen
    2.68
    chyné
    2.62
    <unused23>
    2.61
    <unused1592>
    2.61
    POSITIVE LOGITS
    ↵↵
    4.68
    ↵
    4.59
    ↵↵↵
    3.82
    ↵↵↵↵
    3.10
    ↵↵↵↵↵
    3.04
    <eos>
    2.78
    ↵↵↵↵↵↵
    2.67
    <start_of_image>
    2.58
    ↵↵↵↵↵↵↵
    2.48
    ‬
    2.48
    Activations Density 0.929%

    No Known Activations