© 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. 114064
    Prev
    Next
    INDEX
    Explanations

    named entity followed by specific continuation

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

    This neuron detects capitalized code identifiers or type/property names (PascalCase tokens) in programming 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
     they
    -1.61
     but
    -1.55
     primeiros
    -1.48
     or
    -1.47
    悯
    -1.41
     estamos
    -1.41
     lascia
    -1.38
    ですが
    -1.38
     are
    -1.37
     я
    -1.33
    POSITIVE LOGITS
     összefoglal
    1.60
    edì
    1.51
    ์
    1.50
    '
    1.45
    
    1.45
    oirs
    1.45
     forests
    1.44
     összefoglaló
    1.40
     различни
    1.38
     suéter
    1.38
    Activations Density 0.058%

    No Known Activations