© 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. 1772
    Prev
    Next
    INDEX
    Explanations

    wig types, Zensunni Wanderers

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

    This neuron responds to specific named entities or category labels (proper nouns and titles).

    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
    🎖
    1.02
     miliar
    0.80
     সৈন্য
    0.78
    т
    0.77
     পাকসেন
    0.77
    🌦
    0.77
    最优
    0.75
    🏆
    0.75
    variance
    0.74
    💖
    0.74
    POSITIVE LOGITS
     Feliz
    0.96
     ด
    0.89
     จ
    0.87
    ﺤ
    0.87
     Nov
    0.85
     Bakery
    0.84
     Avenida
    0.83
    ﺣ
    0.82
     Feb
    0.81
     الك
    0.81
    Activations Density 0.062%

    No Known Activations