© 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. 114186
    Prev
    Next
    INDEX
    Explanations

    licensed under, downloaded on

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

    The neuron fires on “Licensed” lines in code comment headers (e.g. the “Licensed under the MIT License” marker).

    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
     varias
    -2.16
     encompasses
    -1.89
     facilitates
    -1.83
     if
    -1.83
    ၜ
    -1.82
     longstanding
    -1.80
    ۸
    -1.79
     enhances
    -1.78
     burgeoning
    -1.73
    Creating
    -1.69
    POSITIVE LOGITS
    ..........
    1.85
     insanely
    1.78
    渽
    1.73
     spectacular
    1.72
     exceptionally
    1.71
     effectuer
    1.71
     anunció
    1.70
     REALLY
    1.70
    "…
    1.70
     magnificent
    1.70
    Activations Density 0.000%

    No Known Activations