© 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. 81181
    Prev
    Next
    INDEX
    Explanations

    seasonal patterns

    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
     hadas
    -0.74
    ktion
    -0.72
    ปล
    -0.72
     fré
    -0.71
     hali
    -0.71
    CATEGORY
    -0.70
    {:
    -0.69
     Vecchio
    -0.69
    Natürlich
    -0.69
    ascending
    -0.68
    POSITIVE LOGITS
     order
    0.83
     seasonal
    0.82
     AR
    0.82
    Saturation
    0.80
     season
    0.77
    𝕝
    0.75
     seasonally
    0.75
     移
    0.73
     Box
    0.72
    obox
    0.72
    Activations Density 0.009%

    No Known Activations