© 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. 8473
    Prev
    Next
    INDEX
    Explanations

    The neuron fires most strongly on single, standalone topic or category words (often capitalized) used as headings—e.g. “Looking,” “Christmas,” “Buffet,” “Outdoor.”

    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
     lastname
    0.70
    جراء
    0.67
     Vestone
    0.67
     controladores
    0.67
    Quantidade
    0.66
     रिसी
    0.66
    闼
    0.66
    ते
    0.64
    Asimismo
    0.64
    闥
    0.64
    POSITIVE LOGITS
    ation
    0.78
    om
    0.75
    aj
    0.73
    fjord
    0.70
    aping
    0.69
    ing
    0.68
    um
    0.67
    ouss
    0.67
    classpath
    0.67
    oted
    0.67
    Activations Density 0.001%

    No Known Activations