© 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. 31-GEMMASCOPE-2-RES-16K
    7. 6867
    Prev
    Next
    INDEX
    Explanations

    invoice number

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

    The neuron activates on tokens that are parts of alphanumeric identifiers—e.g. document or application numbers, legal citation numbers, bar‐codes, and other reference codes.

    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
    🆓
    0.67
    áci
    0.66
    calup
    0.65
    куси
    0.64
    <unused1999>
    0.63
    fillna
    0.63
     മുതൽ
    0.63
    ㍉
    0.63
    釦
    0.63
    <unused52>
    0.62
    POSITIVE LOGITS
     ID
    1.21
     №
    1.20
    编号
    1.16
     #
    1.12
     number
    1.10
    ID
    1.10
     nomor
    1.09
     No
    1.09
    番号
    1.09
     شماره
    1.08
    Activations Density 0.451%

    No Known Activations