© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 55994
    Prev
    Next
    INDEX
    Explanations

    introducing volunteer

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    Package
    -0.85
     Campaign
    -0.78
     Modeling
    -0.77
     Cam
    -0.77
     смысл
    -0.75
     Bloom
    -0.74
    Bloom
    -0.74
    ServletConfig
    -0.73
     Contest
    -0.73
    misen
    -0.71
    POSITIVE LOGITS
     volunteer
    1.09
     barcode
    1.09
    volunteer
    1.01
     Barcode
    1.01
     volunteering
    0.98
     vrijwilli
    0.97
     tourists
    0.94
    Volunteer
    0.92
     weekly
    0.90
    argento
    0.90
    Activations Density 0.001%

    No Known Activations