© 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. 15713
    Prev
    Next
    INDEX
    Explanations

    file extensions or security terms

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

    This neuron detects tokens that occur in bibliographic citations or reference‐list entries (e.g. titles, volume/issue numbers, page ranges, years).

    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
    亜
    0.77
    长大
    0.73
    ум
    0.71
    ア
    0.71
     ca
    0.68
    ал
    0.68
    го
    0.67
     アル
    0.67
    মন্ত্রী
    0.66
     clang
    0.66
    POSITIVE LOGITS
    årt
    0.79
    casualties
    0.78
    utacji
    0.77
    τικών
    0.76
    ີ່
    0.75
    ശന
    0.75
     términos
    0.73
    διο
    0.72
     والمت
    0.71
     prévue
    0.71
    Activations Density 0.000%

    No Known Activations