© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 10954
    Prev
    Next
    INDEX
    Explanations

    emergency numbers

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

    The neuron strongly activates on numeric tokens (numbers and numerical values) in the text.

    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
    ৪
    0.88
    전자
    0.70
    정
    0.68
    σιμο
    0.66
    gehend
    0.66
    한다고
    0.66
     Contempor
    0.66
    стви
    0.65
    정이
    0.65
    นิด
    0.65
    POSITIVE LOGITS
     reprogramming
    0.68
    ⁄
    0.62
     pooling
    0.60
     confronting
    0.59
     তাকে
    0.57
     sacking
    0.56
    ியார்
    0.55
     profits
    0.54
     जबर
    0.54
    рыма
    0.54
    Activations Density 0.135%

    No Known Activations