© 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. 48747
    Prev
    Next
    INDEX
    Explanations

    audience

    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
     activit
    -0.87
     omt
    -0.86
     activists
    -0.86
     activity
    -0.84
    alba
    -0.79
    activity
    -0.77
     Kohler
    -0.77
     activ
    -0.77
     weapon
    -0.76
     activities
    -0.76
    POSITIVE LOGITS
     audience
    3.30
     audiences
    3.17
    audience
    2.41
    Audience
    2.02
     Audience
    2.02
    Audiences
    1.84
     Publikum
    1.75
     ауди
    1.71
    audi
    1.67
     wider
    1.65
    Activations Density 0.038%

    No Known Activations