© 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. 58024
    Prev
    Next
    INDEX
    Explanations

    enterprise business

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

    The neuron strongly responds to common English function words—especially conjunctions and prepositions like “and,” “of,” “as,” and “an”—that typically link items or clauses in feature-list or product‐description sentences.

    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
    Although
    -2.13
    Despite
    -2.05
    During
    -2.02
    There
    -1.92
     but
    -1.91
    Many
    -1.88
    However
    -1.87
    When
    -1.84
    妩
    -1.82
     cukru
    -1.80
    POSITIVE LOGITS
     your
    2.53
    靭
    2.13
    靱
    1.91
     now
    1.85
     zaragoza
    1.74
     rosario
    1.70
     nagu
    1.69
     habang
    1.66
     philippe
    1.63
    рѣ
    1.63
    Activations Density 0.272%

    No Known Activations