© 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. 62885
    Prev
    Next
    INDEX
    Explanations

    subscribe to 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
    ilor
    -0.96
    ExtendWith
    -0.91
    ActionListener
    -0.88
    ха
    -0.87
    封闭
    -0.80
     Deloitte
    -0.77
    AccessorTable
    -0.77
    Volley
    -0.76
    siv
    -0.75
     Dich
    -0.75
    POSITIVE LOGITS
     event
    1.48
     Event
    1.25
     events
    1.24
    event
    1.15
     Events
    1.13
     bus
    1.11
    EventBus
    1.05
    Event
    1.05
    events
    1.04
    EVENT
    1.04
    Activations Density 0.001%

    No Known Activations