© 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
    2. Gemma-3-1B-IT
    3. 17-GEMMASCOPE-2-RES-16K
    4. 1491
    Prev
    Next
    INDEX
    Explanations

    function arguments and returns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-it/resid_post/layer_17_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     tight
    0.83
    ↵↵
    0.77
     finalized
    0.77
     airtight
    0.76
     tightened
    0.75
     customizing
    0.75
     capitalized
    0.75
     concealing
    0.75
     (_)
    0.74
     customized
    0.73
    POSITIVE LOGITS
    Note
    0.81
    ```
    0.81
     Можно
    0.80
    Args
    0.80
     Например
    0.80
    Example
    0.73
    For
    0.72
    :
    0.71
    */
    0.70
    例如
    0.70
    Activations Density 0.277%

    No Known Activations