© 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. 10-GEMMASCOPE-RES-131K
    7. 68548
    Prev
    Next
    INDEX
    Explanations

    describing methods or tools

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

    The neuron primarily detects the word “using” when it appears in text.

    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_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     was
    -3.17
    ’
    -3.05
     '
    -2.48
    на
    -2.42
    や
    -2.23
    是一个
    -2.20
    之心
    -2.17
    的
    -2.14
    等人
    -2.09
    z
    -2.05
    POSITIVE LOGITS
    美国的
    2.44
     the
    2.19
    と言い
    2.17
     Konkurrenz
    2.13
     Realität
    2.03
     одежда
    2.02
     evoke
    2.02
     bekannten
    2.02
     Bildern
    2.00
    いくつかの
    2.00
    Activations Density 0.106%

    No Known Activations