© 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. 31-GEMMASCOPE-2-RES-16K
    7. 6371
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and code delimiters

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

    The neuron activates on inline reference markers or citation superscripts (e.g. “^1234” and similar footnote/reference indicators).

    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
     Chemie
    0.66
     nível
    0.56
     ette
    0.54
    ，$
    0.54
     Authors
    0.52
    ljen
    0.52
     overruled
    0.52
    ิค
    0.52
    ishable
    0.52
    <bbox>
    0.52
    POSITIVE LOGITS
     }_{
    0.60
    prime
    0.59
    假日
    0.59
     worrying
    0.57
    *}{
    0.57
    賴
    0.57
    왕
    0.56
    ܬܐ
    0.55
     प्राइम
    0.54
    夯
    0.54
    Activations Density 0.102%

    No Known Activations