© 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. 115434
    Prev
    Next
    INDEX
    Explanations

    financial regulation

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

    The neuron fires on Spanish-language proper names, especially components of formal agency names (e.g. Comisión Nacional Bancaria y de Valores).

    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
    structed
    -0.77
     beetroot
    -0.76
    tvguidetime
    -0.73
    меты
    -0.72
    ఓ
    -0.70
     Conley
    -0.70
     municipio
    -0.69
    ❿
    -0.68
     ratify
    -0.68
     Équipe
    -0.67
    POSITIVE LOGITS
     regulators
    1.77
     regulator
    1.67
     supervision
    1.48
    regulator
    1.41
     Supervision
    1.41
    REGUL
    1.36
     regulatory
    1.31
     supervisory
    1.30
     Regulator
    1.30
     supervisors
    1.28
    Activations Density 0.023%

    No Known Activations