© 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. 31-GEMMASCOPE-2-RES-16K
    7. 6826
    Prev
    Next
    INDEX
    Explanations

    phone numbers

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

    The neuron detects numeric tokens—strings of digits (e.g. phone numbers, dates, measurements).

    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
     longe
    0.58
    فق
    0.52
     tek
    0.51
    dresser
    0.50
    بتدي
    0.50
    侔
    0.49
    لع
    0.49
    Cober
    0.48
    LaunchAction
    0.48
    getHeader
    0.48
    POSITIVE LOGITS
    Ⴉ
    0.63
     ý
    0.51
     lodged
    0.50
    ారె
    0.50
    обс
    0.49
    óm
    0.48
    ㅌ
    0.47
     yarn
    0.47
     dilapidated
    0.47
     cual
    0.47
    Activations Density 0.199%

    No Known Activations