© 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. 6384
    Prev
    Next
    INDEX
    Explanations

    The neuron primarily responds to content-bearing words (nouns, adjectives, and main verbs) rather than function 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
     permittee
    0.61
    㥆
    0.58
     både
    0.57
     adjustable
    0.56
     zowel
    0.56
     userId
    0.56
    াপিত
    0.55
     (=
    0.54
     Occupational
    0.53
     Verkehrs
    0.53
    POSITIVE LOGITS
     superstars
    0.68
     skyscrapers
    0.67
    America
    0.66
    ჟ
    0.66
     billionaires
    0.63
     ouro
    0.63
     sweeter
    0.61
     بیشتر
    0.61
     περισσότε
    0.61
     الحكومة
    0.61
    Activations Density 0.170%

    No Known Activations