© 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. 56052
    Prev
    Next
    INDEX
    Explanations

    organization, company, business

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

    This neuron fires on formal corporate‐profile language—terms and phrases describing a company’s founding, headquarters, products, and distribution network.

    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
     presumably
    -1.37
     relatively
    -1.24
    を読んで
    -1.20
     balcón
    -1.20
     definitely
    -1.18
     oczywiście
    -1.17
     kemungkinan
    -1.14
    利
    -1.14
     actually
    -1.13
     bezpečnost
    -1.12
    POSITIVE LOGITS
    rizona
    1.52
    neling
    1.20
    demic
    1.14
     kitu
    1.13
     distante
    1.13
     '-':
    1.12
    ῷ
    1.11
     visiter
    1.10
    quire
    1.09
    raisers
    1.09
    Activations Density 0.060%

    No Known Activations