© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 12552
    Prev
    Next
    INDEX
    Explanations

    periods of inactivity or time

    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_22/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
    cação
    -1.10
     ještě
    -1.03
     chacune
    -1.02
     at
    -0.98
     thorium
    -0.95
    klär
    -0.93
     считают
    -0.92
     ngay
    -0.90
     thuy
    -0.90
    镭
    -0.89
    POSITIVE LOGITS
     hiatus
    1.22
     previous
    1.08
    Previous
    1.05
     dormant
    0.95
    Ų
    0.94
     anteriores
    0.94
     inactivity
    0.92
     intervening
    0.91
    等待
    0.89
    leyeb
    0.86
    Activations Density 0.051%

    No Known Activations