© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 59544
    Prev
    Next
    INDEX
    Explanations

    Time Out awards

    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
    titem
    -0.82
     Слу
    -0.75
     Ascot
    -0.74
    ternos
    -0.73
     exterior
    -0.73
     oliveira
    -0.73
    VStack
    -0.72
    ѓ
    -0.71
    ichts
    -0.71
    acinth
    -0.71
    POSITIVE LOGITS
     Timeout
    1.56
    TimeOut
    1.32
     timeout
    1.32
    TIMEOUT
    1.27
    timeout
    1.22
    Timeout
    1.20
     Time
    1.05
    City
    1.04
     City
    0.97
     metropolis
    0.92
    Activations Density 0.044%

    No Known Activations