© 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. 48137
    Prev
    Next
    INDEX
    Explanations

    individual and official capacity

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

    This neuron spotlights legal-style role or capacity phrases (e.g. “in his official capacity”).

    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
    ➧
    -0.84
    DOCX
    -0.79
     クラス
    -0.76
    Opportun
    -0.74
     Rendez
    -0.70
    捷
    -0.70
     gerichtet
    -0.69
     [/
    -0.68
    Mara
    -0.67
     désolés
    -0.67
    POSITIVE LOGITS
     capacity
    3.88
     capacities
    3.03
    capacity
    3.03
    Capacity
    2.92
     Capacity
    2.77
     role
    2.48
    CAPACITY
    2.34
     roles
    2.23
     CAPACITY
    2.22
     capacidad
    1.97
    Activations Density 0.051%

    No Known Activations