© 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. 13119
    Prev
    Next
    INDEX
    Explanations

    te dejo, te resumo, te presento, te detallo

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

    The neuron activates strongly on non-English words or foreign language segments, effectively flagging multilingual or foreign text in the document.

    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
     மற்றும்
    0.67
     (
    0.63
     또는
    0.61
     hoặc
    0.60
    ally
    0.59
     દ્વારા
    0.57
    ays
    0.56
     ("
    0.56
    または
    0.55
    ations
    0.55
    POSITIVE LOGITS
     hicimos
    0.65
     chciał
    0.64
    ﺗ
    0.64
     decía
    0.63
     وصلنا
    0.63
     hacemos
    0.61
    রকম
    0.61
     quería
    0.60
     চাহিল
    0.60
    وو
    0.59
    Activations Density 0.023%

    No Known Activations