© 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-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 9397
    Prev
    Next
    INDEX
    Explanations

    refusals to inappropriate requests

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron strongly fires on document‐structure markers and section introductions—i.e. on the first words or headings that begin new sections or paragraphs.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_31_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
    नीचर
    0.62
    wso
    0.54
     lehet
    0.52
    owi
    0.51
     venons
    0.50
    ቸ
    0.50
     až
    0.50
    derdag
    0.50
     nationalists
    0.49
    ല്ലാം
    0.48
    POSITIVE LOGITS
    <start_of_image>
    1.74
     […]
    1.04
     Continue
    1.04
     [...]
    1.02
    [...]
    1.00
    ↵↵↵
    0.97
    Continue
    0.96
    ↵
    0.93
    続きを読む
    0.92
    ↵↵↵↵
    0.90
    Activations Density 0.260%

    No Known Activations