© 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
    2. Gemma-3-12B
    3. 24-GEMMASCOPE-2-RES-16K
    4. 8841
    Prev
    Next
    INDEX
    Explanations

    The neuron fires on system‐message phrases announcing that an email has been sent to the user (e.g. “email,” “you,” “sent,” “soon as”).

    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
    ючи
    0.78
     modèles
    0.75
    Montgomery
    0.75
    Reynolds
    0.74
    şte
    0.74
    žel
    0.69
    matrices
    0.69
    ﺲ
    0.69
    fony
    0.68
    Aly
    0.68
    POSITIVE LOGITS
     casilla
    0.84
     siguientes
    0.83
     horario
    0.77
     রেখে
    0.77
     queue
    0.76
     Queue
    0.75
     transmisión
    0.75
     সাপ্তাহিক
    0.75
     இருப்பினும்
    0.75
     puja
    0.75
    Activations Density 0.005%

    No Known Activations