© 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. 34546
    Prev
    Next
    INDEX
    Explanations

    market reports and company names

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

    The neuron strongly activates on industry‐report headings—terms like “Market Share,” “Manufacturers,” “Company Profiles,” “Top 10 Countries,” etc.—i.e. section titles and key labels in business/market‐research reports.

    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
     cír
    -1.37
     even
    -1.29
     everything
    -1.28
     so
    -1.23
     just
    -1.22
     not
    -1.19
     two
    -1.18
     voulait
    -1.16
    mbal
    -1.12
     vuestros
    -1.12
    POSITIVE LOGITS
     Konink
    1.18
    וּ
    1.09
     formid
    1.09
     SNOW
    1.07
     mäng
    1.05
     INFIN
    1.05
     pittores
    1.05
     gebre
    1.05
     القرار
    1.05
    Tangent
    1.03
    Activations Density 0.001%

    No Known Activations