© 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. 34-GEMMASCOPE-RES-131K
    7. 7906
    Prev
    Next
    INDEX
    Explanations

    Maine Supreme Judicial Court

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

    The neuron is triggered by metadata header fields and boilerplate declarations (e.g. “Name:”, “This program is free software”, HTML `<meta>` tags, license‐ and copyright‐style lines).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     Pilih
    -0.81
     Bagaimana
    -0.80
     Siapa
    -0.79
    SupportActionBar
    -0.78
     ranchers
    -0.78
    稗
    -0.77
    就任
    -0.77
     Ukuran
    -0.75
    外部
    -0.74
    boli
    -0.74
    POSITIVE LOGITS
    Maine
    1.24
     Maine
    1.23
     Dartmouth
    1.07
    metis
    0.95
     lobster
    0.94
     lobsters
    0.88
     Granite
    0.84
     Massachusetts
    0.82
     Pena
    0.81
    🦞
    0.81
    Activations Density 0.002%

    No Known Activations