© 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. 30473
    Prev
    Next
    INDEX
    Explanations

    labels and details

    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
    內容簡介
    -1.52
     Rusia
    -1.47
     tissus
    -1.34
     PÅ
    -1.34
     Timoteo
    -1.31
     arbre
    -1.29
    Имя
    -1.28
    Reak
    -1.27
     berge
    -1.26
    
    -1.26
    POSITIVE LOGITS
     type
    1.70
     where
    1.54
     location
    1.45
     number
    1.40
    ,
    1.38
     to
    1.36
     available
    1.33
     can
    1.33
     estimated
    1.30
    h
    1.29
    Activations Density 0.039%

    No Known Activations