© 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. 10-GEMMASCOPE-RES-131K
    7. 71980
    Prev
    Next
    INDEX
    Explanations

    night time and 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_10/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
    0
    -3.17
    ).
    -2.88
    偸
    -2.25
    ”.
    -2.19
     to
    -2.00
    也算是
    -1.97
    𐄙
    -1.95
     всем
    -1.91
    稣
    -1.88
     tématu
    -1.87
    POSITIVE LOGITS
     nights
    2.69
     Nights
    2.25
    ’
    2.17
    嬗
    2.02
    岀
    1.99
     konus
    1.91
    熒
    1.87
    if
    1.85
    Nights
    1.85
     selben
    1.82
    Activations Density 0.002%

    No Known Activations