© 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. 77668
    Prev
    Next
    INDEX
    Explanations

    Expo event

    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
    COACH
    -0.81
    UserType
    -0.74
    ėl
    -0.73
     hout
    -0.72
    Stell
    -0.71
    ACKNOWLEDGMENT
    -0.71
     Negotiation
    -0.70
    MouseListener
    -0.70
     театр
    -0.70
     Ducati
    -0.69
    POSITIVE LOGITS
     Expo
    1.28
    Expo
    1.19
     expo
    1.14
     EXPO
    1.09
    expo
    0.98
     Constants
    0.88
     Barnet
    0.87
    Evening
    0.80
     Exposition
    0.80
     уют
    0.79
    Activations Density 0.016%

    No Known Activations