© 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. 63413
    Prev
    Next
    INDEX
    Explanations

    execute, connect, start, close, set, invoke, discover

    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
     детали
    -0.89
    èm
    -0.75
    mig
    -0.75
     Abund
    -0.70
     illeg
    -0.69
    chtete
    -0.69
    akal
    -0.69
    Specyfikacja
    -0.69
     Embrace
    -0.68
    でん
    -0.68
    POSITIVE LOGITS
     shutdown
    1.07
     close
    1.07
     await
    0.93
    close
    0.90
    await
    0.85
    sendStatus
    0.84
     closing
    0.84
     submit
    0.79
     closure
    0.78
     stopping
    0.77
    Activations Density 0.012%

    No Known Activations