© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 3230
    Prev
    Next
    INDEX
    Explanations

    pages and section titles

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

    The neuron fires on document metadata codes and numbers—things like form or guide numbers, page references, and other numeric identifiers.

    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_24_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
     ब्लॉग
    0.67
    ⚭
    0.66
    ↝
    0.63
    💰
    0.62
     tı
    0.60
     aspekt
    0.60
     কাজকর্ম
    0.60
    🗸
    0.60
     전쟁
    0.60
     الوزن
    0.60
    POSITIVE LOGITS
     www
    0.86
    www
    0.74
     photoc
    0.63
     photocopy
    0.60
    PAGE
    0.58
    1
    0.58
    2
    0.57
    Page
    0.57
    <0x0C>
    0.56
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    0.53
    Activations Density 0.013%

    No Known Activations