© 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. 34-GEMMASCOPE-RES-131K
    7. 77976
    Prev
    Next
    INDEX
    Explanations

    find listings or projects

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

    The neuron consistently lights up on promotional or marketing language describing a product/service platform and its features or capabilities.

    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
    EmployeeId
    -0.97
     Mitarbeiter
    -0.90
     фигур
    -0.89
     Vertrieb
    -0.86
     Employees
    -0.85
     Employee
    -0.80
    낸
    -0.78
    Betting
    -0.78
    xticks
    -0.76
     продаж
    -0.76
    POSITIVE LOGITS
     listing
    1.73
     listings
    1.67
     matching
    1.62
     posting
    1.57
     posted
    1.54
     registered
    1.46
    Matching
    1.42
    匹配
    1.41
     listed
    1.40
    Listing
    1.38
    Activations Density 0.074%

    No Known Activations