© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 34757
    Prev
    Next
    INDEX
    Explanations

    industry sectors

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

    The neuron fires strongly on terms naming economic sectors or industries (e.g. Oil & Gas, pharmaceuticals, healthcare, biotech, technology, travel).

    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
    総評
    -1.37
     that
    -1.28
     amado
    -1.21
     enamorado
    -1.20
     atún
    -1.19
    寝る
    -1.16
     garantiert
    -1.15
    uebas
    -1.15
     owing
    -1.13
     partículas
    -1.12
    POSITIVE LOGITS
     industry
    1.95
     sector
    1.61
     is
    1.30
    specific
    1.30
     فيه
    1.25
    厚度
    1.23
     companies
    1.23
    accurate
    1.21
     giants
    1.20
    related
    1.16
    Activations Density 0.051%

    No Known Activations