© 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. 22-GEMMASCOPE-RES-131K
    7. 95677
    Prev
    Next
    INDEX
    Explanations

    businesses and organizations

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

    The neuron activates on formal regulatory or legal language—especially licensing terms, agency or company names, and statute-style 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_22/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
    のかも
    -1.31
     considerazione
    -1.19
    わけで
    -1.11
     potrebbe
    -1.11
    ῖς
    -1.09
     verbessert
    -1.09
    為に
    -1.09
    ghh
    -1.07
    iestety
    -1.06
     probablement
    -1.05
    POSITIVE LOGITS
     económica
    1.35
     regulations
    1.34
     businesses
    1.31
     permitted
    1.26
     operate
    1.25
    gione
    1.23
     must
    1.19
     companies
    1.16
     who
    1.15
     (§
    1.15
    Activations Density 0.047%

    No Known Activations