© 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
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 12258
    Prev
    Next
    INDEX
    Explanations

    foreign language

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

    The neuron flags unusually informative or rare words—particularly proper names, domain‐specific terms, and other low-frequency “content” 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
     portátil
    0.83
     mascot
    0.81
    ?»
    0.81
     cinc
    0.80
     infraestructura
    0.77
    u
    0.77
     malpractice
    0.76
     fisheries
    0.75
     revolver
    0.75
     nonfiction
    0.75
    POSITIVE LOGITS
    ни
    0.86
    便是
    0.80
    חה
    0.74
    數
    0.73
     связан
    0.73
    턴
    0.73
    йна
    0.72
     рабо
    0.71
    гу
    0.70
     দেশটির
    0.70
    Activations Density 0.000%

    No Known Activations