© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 102460
    Prev
    Next
    INDEX
    Explanations

    legal code or regulation

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

    The neuron fires on numeric tokens and legal‐style section/citation numbers (e.g. statute or code references).

    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
     Section
    -0.88
     §
    -0.82
    het
    -0.73
     gemäß
    -0.70
    Далее
    -0.69
    gridLayout
    -0.69
     Nationalism
    -0.68
    new
    -0.68
    沙拉
    -0.68
     согласно
    -0.67
    POSITIVE LOGITS
     Code
    1.11
     code
    0.95
    Code
    0.94
     of
    0.94
     código
    0.90
    hecta
    0.79
    icode
    0.79
     CODE
    0.78
     codigo
    0.78
    有一定
    0.78
    Activations Density 0.040%

    No Known Activations