© 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. 2291
    Prev
    Next
    INDEX
    Explanations

    legal or formal citations

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

    This neuron detects formal legal or legislative wording and citation markers (e.g. “Whereas,” section numbers, “Constitution,” “provides,” dates, and similar legal-document jargon).

    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
     districts
    -0.88
     Vorteile
    -0.85
    turismo
    -0.84
     conseillé
    -0.84
    anada
    -0.83
     ſome
    -0.83
    nominal
    -0.83
     približ
    -0.82
     Verfahren
    -0.81
     valgt
    -0.81
    POSITIVE LOGITS
     sấy
    0.96
     suffers
    0.92
    斐
    0.91
    ઁ
    0.88
    魚
    0.88
     Erm
    0.87
    rile
    0.87
    ametric
    0.86
    oben
    0.86
     admittedly
    0.85
    Activations Density 0.001%

    No Known Activations