© 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. 34-GEMMASCOPE-RES-131K
    7. 91277
    Prev
    Next
    INDEX
    Explanations

    speech and debate competitions

    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
    ugou
    -0.84
    웁
    -0.80
     
    -0.77
     Schilling
    -0.77
    fizierung
    -0.76
     expat
    -0.75
     mlb
    -0.73
    打卡
    -0.73
     مهند
    -0.73
     ehrlich
    -0.72
    POSITIVE LOGITS
     debate
    1.68
     Debate
    1.32
     argument
    1.30
     speech
    1.28
     tournaments
    1.28
    Debate
    1.27
     debat
    1.22
    debate
    1.22
    Argument
    1.21
     argue
    1.21
    Activations Density 0.011%

    No Known Activations