© 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. 22606
    Prev
    Next
    INDEX
    Explanations

    related to self-reference and interfaces

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

    This neuron activates on unusually long or technical content words (i.e. tokens with many characters).

    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
     vuoden
    -1.42
     heeft
    -1.41
     stammen
    -1.38
     exámenes
    -1.34
     tatuajes
    -1.33
    ifornia
    -1.33
     kuitenkin
    -1.33
     amalgamation
    -1.33
    ecar
    -1.28
    礴
    -1.27
    POSITIVE LOGITS
    儅
    1.40
     influenci
    1.34
     won
    1.29
     only
    1.28
    Two
    1.28
     until
    1.27
     where
    1.26
     anest
    1.24
    How
    1.23
     current
    1.22
    Activations Density 0.190%

    No Known Activations