© 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. 3114
    Prev
    Next
    INDEX
    Explanations

    programming constructs and code

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

    This neuron is highly active on numeric tokens with decimal points (e.g. volume.issue, page numbers, DOIs) 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
    dı
    1.05
    ௐ
    1.03
    ong
    1.01
     由
    1.00
    lerim
    0.97
    㬰
    0.95
    ^{*
    0.90
    𝚗
    0.89
     求
    0.88
    ани
    0.88
    POSITIVE LOGITS
    ش
    0.79
     Panel
    0.75
    Jump
    0.74
     erle
    0.71
     birinci
    0.70
    係る
    0.69
    Image
    0.68
     أعلى
    0.68
     gewährle
    0.68
     منابع
    0.68
    Activations Density 0.000%

    No Known Activations