© 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. 34-GEMMASCOPE-RES-131K
    7. 91302
    Prev
    Next
    INDEX
    Explanations

    time periods

    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
    tyw
    -0.85
    versaire
    -0.75
    playlist
    -0.74
    ográfica
    -0.73
     literario
    -0.73
     nhàng
    -0.73
    Occurs
    -0.72
    Dichloroethane
    -0.71
    olu
    -0.70
    Ply
    -0.70
    POSITIVE LOGITS
     period
    6.00
    period
    4.13
    Period
    3.92
     periods
    3.86
     Period
    3.80
     période
    3.70
     período
    3.53
    PERIOD
    3.30
     periodo
    3.28
     период
    3.25
    Activations Density 0.150%

    No Known Activations