© 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. 65640
    Prev
    Next
    INDEX
    Explanations

    legal document case numbers

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

    The neuron fires on numeric tokens and identifiers—anything that looks like a number (version numbers, docket or file IDs, years, etc.).

    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
     runs
    -0.73
    齊
    -0.68
     demur
    -0.67
     redo
    -0.64
     first
    -0.64
    getClass
    -0.62
     роль
    -0.61
     based
    -0.60
    usty
    -0.60
    事実
    -0.60
    POSITIVE LOGITS
    терак
    1.04
    cinogen
    0.70
     אח
    0.69
    ત
    0.68
    Projects
    0.68
    ouwen
    0.68
    вають
    0.68
     conclure
    0.67
     garçon
    0.66
     família
    0.66
    Activations Density 0.077%

    No Known Activations