© 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. 1463
    Prev
    Next
    INDEX
    Explanations

    numbers and technical terms

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

    This neuron activates on numeric digit tokens—especially sequences of digits formatted like 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
     $_{\
    0.66
     त्यानंतर
    0.65
     kemudian
    0.62
     skutecz
    0.61
     anschließend
    0.61
     केल्यानंतर
    0.60
    その後
    0.59
     zwró
    0.58
    ̧
    0.58
     $^{\
    0.58
    POSITIVE LOGITS
     congressman
    0.62
     रोमांटिक
    0.60
     PHONE
    0.59
     journée
    0.59
     놀
    0.58
    Ť
    0.56
     นาที
    0.55
     Powell
    0.55
     hotline
    0.55
     delights
    0.55
    Activations Density 0.005%

    No Known Activations