© 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. 10-GEMMASCOPE-RES-131K
    7. 105609
    Prev
    Next
    INDEX
    Explanations

    family owned business

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

    This neuron activates on mentions of “family-owned” businesses (often in the phrase “family-owned and operated” or similar).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     in
    -1.66
     to
    -1.63
     two
    -1.55
     Having
    -1.51
     for
    -1.48
     six
    -1.48
     difficult
    -1.44
     dazzling
    -1.44
    S
    -1.41
     all
    -1.40
    POSITIVE LOGITS
     centaines
    1.63
     Atención
    1.57
     pittores
    1.49
     rése
    1.48
     Dinas
    1.48
     HUND
    1.47
     offrant
    1.47
     legendar
    1.45
    cheers
    1.44
     pourront
    1.44
    Activations Density 0.027%

    No Known Activations