© 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. 87054
    Prev
    Next
    INDEX
    Explanations

    cold turkey

    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
     Flea
    -0.88
    ↬
    -0.84
     negate
    -0.75
     Émile
    -0.72
    其余
    -0.72
     Cavaliers
    -0.70
     dès
    -0.70
     Mongols
    -0.69
    AUTOR
    -0.68
     củ
    -0.68
    POSITIVE LOGITS
     turkey
    2.08
     Turkey
    1.95
    Turkey
    1.84
    turkey
    1.58
     turkeys
    1.49
    🦃
    1.40
     cold
    1.40
    cold
    1.21
     poul
    1.19
     ترکیه
    1.17
    Activations Density 0.037%

    No Known Activations