© 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. 9566
    Prev
    Next
    INDEX
    Explanations

    very end

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

    The neuron fires primarily on numeric tokens (digits or numbers, especially those with decimal points).

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

    numerical digits within structured reference citations or data entries.

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

    numeric data featuring decimal points, often within citations, statistics, or list-like records

    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
     systemat
    0.49
     analyses
    0.47
     delim
    0.47
     exist
    0.46
    .³
    0.45
     equivari
    0.45
     demod
    0.45
     formalized
    0.44
     recognize
    0.44
     equally
    0.44
    POSITIVE LOGITS
    anyard
    0.58
     Màu
    0.57
     Цвет
    0.56
     딱
    0.55
     עבור
    0.54
     Công
    0.54
     Chỉ
    0.54
     Nhưng
    0.52
     Còn
    0.52
     Cualquier
    0.52
    Activations Density 0.105%

    No Known Activations