© 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. 8444
    Prev
    Next
    INDEX
    Explanations

    phone number regex

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

    The neuron strongly activates on formal document signposts and proper designators—words like “Figure,” “Department,” “INC.,” “PATH,” or other section-heading/organization labels that appear in structured or technical texts.

    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
    ação
    0.91
    aan
    0.91
    они
    0.91
    ан
    0.90
    À
    0.89
    iu
    0.88
    ஆன்
    0.87
    ஆ
    0.87
    Т
    0.86
    ак
    0.85
    POSITIVE LOGITS
     calculus
    0.87
     marines
    0.84
     barcodes
    0.81
     cannons
    0.80
     calculators
    0.80
     BES
    0.80
     boomers
    0.79
     Shelter
    0.79
     Phaser
    0.78
     Greenway
    0.78
    Activations Density 0.000%

    No Known Activations