© 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-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 30155
    Prev
    Next
    INDEX
    Explanations

    foreign names and words

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

    This neuron detects tokens that contain non-ASCII letters (i.e. Latin characters with diacritics or other special accents).

    oai_token-act-pair · o4-mini
    Triggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    Before
    -1.10
     increases
    -1.07
     give
    -1.05
    Shortly
    -1.04
    There
    -1.03
     Before
    -1.01
    風險
    -1.00
    Almost
    -0.99
     enhances
    -0.99
     one
    -0.98
    POSITIVE LOGITS
     decidedly
    1.20
    "> 
    1.17
     delightfully
    1.15
     secluded
    1.13
     lauded
    1.13
     flamboyant
    1.10
     wonderfully
    1.10
     descri
    1.09
     スカート
    1.09
     wondrous
    1.08
    Activations Density 0.011%

    No Known Activations