© 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. 2080
    Prev
    Next
    INDEX
    Explanations

    citations and connectors

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

    This neuron detects reference or footnote citation markers (numeric citation indices).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    references or citations in academic/scholarly text, particularly those formatted with numbers in brackets or parentheses.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jyhe0408

    scholarly citation markers and numbered references in academic text, such as bracketed reference numbers, ranges, and footnote notations.

    oai_token-act-pair · gpt-5Triggered 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
    ara
    0.54
    ID
    0.53
    xious
    0.52
    am
    0.50
    CameraButton
    0.49
    ש
    0.48
    State
    0.47
    -
    0.47
    ־
    0.46
    antly
    0.46
    POSITIVE LOGITS
     һәм
    0.70
     және
    0.70
     valamint
    0.59
     รวมถึง
    0.59
    ográf
    0.58
     그리고
    0.58
     Ար
    0.58
     və
    0.57
     Также
    0.56
     oraz
    0.55
    Activations Density 0.005%

    No Known Activations