© 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. 47964
    Prev
    Next
    INDEX
    Explanations

    maxIdleTime configuration setting

    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
     hören
    -0.80
    합
    -0.78
     fans
    -0.76
    Dew
    -0.74
     marten
    -0.74
     Fans
    -0.73
     Player
    -0.72
     fan
    -0.71
     писать
    -0.69
    Autoritní
    -0.69
    POSITIVE LOGITS
    Idle
    1.07
     idle
    1.07
    idle
    0.92
     borrow
    0.91
    borrow
    0.89
     checkout
    0.87
    Loan
    0.85
    checkout
    0.85
     Idle
    0.83
    钝
    0.83
    Activations Density 0.009%

    No Known Activations