© 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. 24-GEMMASCOPE-2-RES-16K
    7. 7249
    Prev
    Next
    INDEX
    Explanations

    phone numbers

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

    The neuron selectively activates on sequences of digits (e.g. phone numbers, long numeric strings).

    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
     kampus
    0.70
     deposito
    0.62
     logins
    0.62
     població
    0.62
     Greenville
    0.62
     consommateurs
    0.61
     или
    0.60
    𝖽
    0.60
     kostenlos
    0.60
     cercanas
    0.60
    POSITIVE LOGITS
    Material
    0.68
    Due
    0.66
     Debido
    0.65
    Antib
    0.63
     Due
    0.57
     Pedal
    0.57
     analogous
    0.56
     由于
    0.56
    由于
    0.55
    mtable
    0.55
    Activations Density 0.034%

    No Known Activations