© 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. 9280
    Prev
    Next
    INDEX
    Explanations

    special characters and punctuation

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

    The neuron activates on numeric tokens and numeric expressions (e.g. standalone numbers, measurements, quantities, and IDs).

    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
    get
    1.38
    set
    1.27
    =
    1.27
    true
    1.25
    data
    1.23
    self
    1.22
    is
    1.21
    code
    1.18
    （
    1.17
    ==
    1.16
    POSITIVE LOGITS
     .)
    1.88
     🤗
    1.69
     👌
    1.68
     ;,
    1.60
     :,
    1.59
     🌱
    1.59
     🙌
    1.59
     ⏮
    1.59
     😏
    1.57
     ۹
    1.56
    Activations Density 1.080%

    No Known Activations