© 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. 1479
    Prev
    Next
    INDEX
    Explanations

    The neuron flags rare or distinctive named entities (proper nouns and titles) in the text.

    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
    น
    0.87
    s
    0.79
    ς
    0.76
    И
    0.76
    س
    0.73
    і
    0.73
    ഭ
    0.73
     Miros
    0.72
    í
    0.72
     unbelievably
    0.71
    POSITIVE LOGITS
     contextos
    0.84
     genutzt
    0.76
     وبين
    0.75
     các
    0.74
    ysen
    0.73
     विविध
    0.71
     solcher
    0.71
    тивних
    0.70
    ሎችን
    0.69
     வடிக
    0.69
    Activations Density 0.004%

    No Known Activations