© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 72843
    Prev
    Next
    INDEX
    Explanations

    eclipse software and licensing

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

    The neuron detects occurrences of the substring “eclipse” (as part of package names, license names, URLs, etc.) in code or documentation.

    oai_token-act-pair · o4-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
    ピアス
    -2.55
    鮃
    -2.39
    /
    -2.27
    猛然
    -2.25
     presentan
    -2.23
    篱
    -2.17
    噩
    -2.14
     piden
    -2.13
     anderen
    -2.11
     institución
    -2.08
    POSITIVE LOGITS
    ↵
    2.91
    摃
    2.73
    嚒
    2.70
    ated
    2.66
     jis
    2.50
    ”،
    2.45
    欵
    2.36
    The
    2.31
     neuem
    2.31
    沕
    2.25
    Activations Density 0.009%

    No Known Activations