© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 102565
    Prev
    Next
    INDEX
    Explanations

    owner or owners

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

    The neuron detects mentions of business owners or entrepreneurs.

    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
     guerres
    -1.48
     accompagner
    -1.47
    儅
    -1.46
    🎺
    -1.44
    <<<<<<<
    -1.40
    zać
    -1.39
     ondes
    -1.38
    ♯
    -1.35
     byproduct
    -1.34
    Александр
    -1.33
    POSITIVE LOGITS
                
    1.68
     Identität
    1.63
    偁
    1.62
     WHAT
    1.60
     also
    1.60
    ylvanian
    1.59
    </strong>
    1.58
    1.52
     and
    1.52
    9
    1.51
    Activations Density 0.016%

    No Known Activations