© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 11073
    Prev
    Next
    INDEX
    Explanations

    want company or ancestry

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

    The neuron fires most strongly on relatively rare or specialized tokens—that is, uncommon vocabulary words.

    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
     three
    0.68
     predicted
    0.68
     four
    0.68
     projected
    0.63
     thirty
    0.61
     test
    0.61
    βα
    0.61
     B
    0.60
    rm
    0.60
     toss
    0.60
    POSITIVE LOGITS
     alku
    0.93
    هایی
    0.90
    evším
    0.88
    های
    0.87
     ampio
    0.86
    不说
    0.86
    
    0.85
     terapi
    0.84
    呯
    0.83
     deiner
    0.81
    Activations Density 0.001%

    No Known Activations