© 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. 5609
    Prev
    Next
    INDEX
    Explanations

    The main thing this neuron does is spot references to external contact or resource links—e.g. phone numbers and URLs.

    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
    会有
    0.99
    말
    0.89
    дон
    0.83
    鐩
    0.82
    買
    0.82
    隨
    0.80
     savages
    0.80
    тріш
    0.79
    痪
    0.79
    杝
    0.79
    POSITIVE LOGITS
     Heraus
    0.86
    ╯
    0.83
    0.77
    ppins
    0.72
    Rek
    0.70
     Weltkrieg
    0.70
    SpringBoot
    0.68
    Parameters
    0.67
    Whitelist
    0.67
    fling
    0.67
    Activations Density 0.000%

    No Known Activations