© 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. 2709
    Prev
    Next
    INDEX
    Explanations

    explanation format

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

    The neuron identifies numeric tokens used in academic citations—such as years, volume and issue numbers, page ranges, and other reference-related digits.

    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
     ’
    0.86
     (’
    0.69
     ’’
    0.66
     “‘
    0.63
    —”
    0.63
    —“
    0.62
     ‘
    0.56
    ,’”
    0.56
    
    0.54
     fi
    0.54
    POSITIVE LOGITS
    .(
    0.60
    (+)
    0.59
    ()(
    0.58
    @(
    0.54
    ](
    0.54
    )(
    0.53
    ).(
    0.52
    "(
    0.51
    ?(
    0.51
    μπ
    0.50
    Activations Density 0.148%

    No Known Activations