© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 5112
    Prev
    Next
    INDEX
    Explanations

    besides regions

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

    The neuron sharply activates on content‐bearing, relatively rare or “important” words (nouns, verbs, adjectives) and stays off for common function words.

    oai_token-act-pair · o4-mini
    Triggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     respectivas
    0.56
     respectivos
    0.54
    atemala
    0.49
    чению
    0.49
    也不会
    0.48
     heller
    0.48
     lentamente
    0.48
    <0x8A>
    0.47
    brado
    0.47
    ላቸው
    0.46
    POSITIVE LOGITS
     besides
    4.38
     selain
    4.28
    besides
    4.00
     além
    3.95
     помимо
    3.91
     aside
    3.63
    Besides
    3.63
    除了
    3.58
     Besides
    3.56
     oltre
    3.53
    Activations Density 0.738%

    No Known Activations