© 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. 8837
    Prev
    Next
    INDEX
    Explanations

    The neuron fires strongly on semantically rich, content‐bearing words (key nouns and verbs) that carry the main informational or instructional substance of a passage.

    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
     (
    0.68
     seem
    0.62
     같이
    0.61
     continual
    0.61
     '
    0.59
     &
    0.59
    或者
    0.59
     stated
    0.58
    ='
    0.58
     noted
    0.57
    POSITIVE LOGITS
     muebles
    0.72
     Möbel
    0.70
     Ubuy
    0.68
    niejs
    0.65
     judíos
    0.65
     terceros
    0.64
     österreich
    0.63
    ʏ
    0.63
    𝗈
    0.63
    ികളുടെ
    0.62
    Activations Density 0.002%

    No Known Activations