© 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. 24-GEMMASCOPE-2-RES-16K
    7. 14931
    Prev
    Next
    INDEX
    Explanations

    emergency call 911

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

    The neuron activates most strongly on multi-digit numeric tokens (e.g. model numbers, dates, 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_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
    up
    0.79
    𝐟
    0.77
    ﹐
    0.76
    
    0.75
    ﹑
    0.75
    DWORD
    0.73
    ♓
    0.73
    unset
    0.71
    JPanel
    0.70
    ...">
    0.70
    POSITIVE LOGITS
     informazioni
    0.76
     Fellow
    0.75
     vict
    0.74
     naturali
    0.74
    是一种
    0.73
     animali
    0.71
     représentation
    0.70
     esperienza
    0.69
    詁
    0.69
     সরবরাহ
    0.68
    Activations Density 0.033%

    No Known Activations