© 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. 92657
    Prev
    Next
    INDEX
    Explanations

    trope

    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
     Christiane
    -0.75
     kiện
    -0.73
     dié
    -0.71
     psal
    -0.71
     Vasily
    -0.71
     Tanja
    -0.70
    ዶ
    -0.70
    틸
    -0.69
     metodi
    -0.68
     Solano
    -0.68
    POSITIVE LOGITS
     trope
    3.25
     tropes
    3.11
     Trop
    2.70
    Trop
    2.55
    trop
    2.50
     Tro
    2.48
    tro
    2.31
     trop
    2.30
    Tro
    2.11
     тро
    2.00
    Activations Density 0.040%

    No Known Activations