© 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. 24-GEMMASCOPE-2-RES-16K
    7. 9348
    Prev
    Next
    INDEX
    Explanations

    Code, prompts, and reports

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

    The neuron strongly activates on numeric citation details—especially on decimal or page‐number tokens in reference entries.

    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
     الزمن
    0.82
    暄
    0.75
     fürs
    0.74
    iselle
    0.74
    borg
    0.73
    zis
    0.73
    ysi
    0.71
    的形式
    0.70
    iosk
    0.70
     grasa
    0.69
    POSITIVE LOGITS
    мі
    0.88
    ді
    0.86
    क
    0.77
    स
    0.76
    ственной
    0.74
    단을
    0.74
    ство
    0.73
    ਦ
    0.73
     Standort
    0.72
    廖
    0.71
    Activations Density 0.001%

    No Known Activations