© 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. 15702
    Prev
    Next
    INDEX
    Explanations

    loan mortgage

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

    This neuron fires on prominent topic‐defining nouns or technical keywords—i.e. the main content words that label the subject of a passage.

    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
     toujours
    -1.48
    licitations
    -1.41
     bailando
    -1.36
    ﹅
    -1.31
    ixante
    -1.30
     tradicional
    -1.24
    urement
    -1.24
    噥
    -1.23
    тент
    -1.23
    зион
    -1.23
    POSITIVE LOGITS
     then
    1.41
     now
    1.30
    /
    1.28
     make
    1.28
    ↵
    1.23
    今後
    1.19
     luego
    1.16
     you
    1.13
     there
    1.13
     help
    1.13
    Activations Density 0.625%

    No Known Activations