© 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. 3392
    Prev
    Next
    INDEX
    Explanations

    days of week

    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
     he
    -0.85
     time
    -0.82
     erst
    -0.81
     wichtigsten
    -0.80
     on
    -0.79
     in
    -0.79
     sometimes
    -0.78
     left
    -0.78
    naments
    -0.77
    ācijas
    -0.77
    POSITIVE LOGITS
     Jul
    1.25
     Apr
    1.02
     parfü
    1.02
    🚬
    0.98
    Regula
    0.94
     parfüm
    0.93
     taches
    0.91
     tromper
    0.90
    Buat
    0.90
     Sep
    0.89
    Activations Density 0.012%

    No Known Activations