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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 124641
    Prev
    Next
    INDEX
    Explanations

    gnome and gnrh

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

    The neuron identifies GNOME desktop environment and GN abbreviation references in technical computing contexts.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    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
    ༑
    -3.06
    珦
    -2.88
    猁
    -2.70
    تیجه
    -2.41
     valentín
    -2.38
    𓋼
    -2.36
    煐
    -2.36
    鹚
    -2.30
    оргаш
    -2.27
    垵
    -2.25
    POSITIVE LOGITS
    '
    3.33
    *
    2.70
     '
    2.36
    >
    2.33
     of
    2.27
    裡的
    2.23
    也
    2.22
     है
    2.14
     knows
    2.11
    "
    2.08
    Activations Density 0.006%

    No Known Activations