© 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. 45404
    Prev
    Next
    INDEX
    Explanations

    transactions and business formation

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

    The neuron fires strongly on legal practice‐area terminology (e.g. “real estate,” “investment,” “counsel,” “litigation,” “business disputes,” 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
     согласно
    -0.85
     BehaviorSubject
    -0.83
     might
    -0.82
     even
    -0.82
    ytick
    -0.77
    국
    -0.77
     अलावा
    -0.74
     if
    -0.74
     explí
    -0.73
    rdom
    -0.73
    POSITIVE LOGITS
     transactional
    1.36
     transactions
    1.16
    Transactional
    1.13
     structuring
    1.09
    deve
    1.00
     matters
    0.98
     drafting
    0.98
    transactions
    0.98
    Formation
    0.93
     formation
    0.92
    Activations Density 0.025%

    No Known Activations