© 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. 6701
    Prev
    Next
    INDEX
    Explanations

    this a it is

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

    This neuron fires on general-purpose, mid-frequency “discourse” words (e.g. such, some, use/using, ability, different, more) that often appear in explanatory or descriptive passages.

    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
    苼
    -1.46
     rése
    -1.44
     extravag
    -1.44
     разгово
    -1.42
     wektor
    -1.42
    
    -1.38
     ganadores
    -1.36
     akumulator
    -1.36
    FRANCE
    -1.34
     calefacción
    -1.34
    POSITIVE LOGITS
     because
    2.13
     there
    1.94
     it
    1.87
     while
    1.76
     will
    1.66
     to
    1.63
     after
    1.62
    after
    1.61
     is
    1.55
     could
    1.54
    Activations Density 0.591%

    No Known Activations