© 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. 24-GEMMASCOPE-2-RES-16K
    7. 807
    Prev
    Next
    INDEX
    Explanations

    The neuron detects sequences of digits used in contact information (e.g. phone numbers).

    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
    ある
    0.52
    ような
    0.48
    কিছু
    0.48
    ধির
    0.48
    つまり
    0.45
    टील
    0.45
    是一種
    0.45
    들
    0.44
    atter
    0.43
    রণ
    0.43
    POSITIVE LOGITS
     fax
    0.66
    telephone
    0.64
     teléfono
    0.64
     phone
    0.63
     telephone
    0.62
     телефо
    0.62
    phone
    0.61
     PHONE
    0.61
    Telephone
    0.61
     Phone
    0.60
    Activations Density 0.061%

    No Known Activations