© 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. 57567
    Prev
    Next
    INDEX
    Explanations

    class definitions and inheritance

    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
    idue
    -0.69
    viewController
    -0.67
     nye
    -0.66
    チャ
    -0.66
     gedachten
    -0.65
     klip
    -0.65
    buttonBar
    -0.65
    dern
    -0.65
     ASUS
    -0.65
     redevelopment
    -0.65
    POSITIVE LOGITS
     Application
    0.89
     application
    0.84
    Application
    0.82
    application
    0.79
    的事情
    0.76
     抓
    0.73
     Plan
    0.71
    Plan
    0.68
    policy
    0.68
    Crane
    0.68
    Activations Density 0.055%

    No Known Activations