© 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. 76091
    Prev
    Next
    INDEX
    Explanations

    legal clauses and provisions

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

    The neuron detects mentions of legal contract terms, especially clauses (e.g. “clause,” “contract,” “release clause”).

    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
    чий
    -0.79
    kreises
    -0.78
    ומות
    -0.78
    meleri
    -0.77
    झ
    -0.75
    EREO
    -0.74
     Minne
    -0.73
    Вам
    -0.73
     Spalding
    -0.73
     Gea
    -0.71
    POSITIVE LOGITS
     clause
    5.19
     clauses
    4.63
    clause
    3.70
     Clause
    3.33
     provisions
    3.23
    Clause
    3.19
    clauses
    3.03
     cláus
    3.03
     Clauses
    2.89
     provision
    2.52
    Activations Density 0.091%

    No Known Activations