© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 106450
    Prev
    Next
    INDEX
    Explanations

    days, mornings, and nights

    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
     tumours
    -0.84
     получилось
    -0.79
    льни
    -0.73
    ⓛ
    -0.71
     desolate
    -0.70
     overnight
    -0.69
     재
    -0.69
     img
    -0.68
    <blockquote>
    -0.68
    OfDay
    -0.68
    POSITIVE LOGITS
    dream
    1.13
    dreaming
    1.09
    lily
    1.06
    dreams
    0.90
    tona
    0.85
    DREAM
    0.85
    OfWeek
    0.83
     рождения
    0.83
    Bulletin
    0.79
    ingale
    0.79
    Activations Density 0.027%

    No Known Activations