© 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. 78278
    Prev
    Next
    INDEX
    Explanations

    Grand Prix series events

    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
     uiteindelijk
    -0.86
    delay
    -0.83
    bashrc
    -0.78
    进
    -0.73
     spotted
    -0.73
    miljø
    -0.73
    сыз
    -0.71
    九年
    -0.71
    Hvem
    -0.71
    游戏
    -0.71
    POSITIVE LOGITS
     stops
    1.48
     stop
    1.41
     event
    1.25
    stops
    1.20
     leg
    1.16
     legs
    1.16
     Stops
    1.15
    Stops
    1.13
     stopping
    0.98
     останов
    0.98
    Activations Density 0.054%

    No Known Activations