© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 62970
    Prev
    Next
    INDEX
    Explanations

    days of the 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
     Tuesday
    -1.65
     Thursday
    -1.63
     Wednesday
    -1.62
     Friday
    -1.55
     Monday
    -1.49
     Sunday
    -1.41
     Saturday
    -1.38
     of
    -1.33
     and
    -1.31
    Thursday
    -1.25
    POSITIVE LOGITS
     régle
    1.16
     résine
    1.05
    bmatrix
    1.03
     atteinte
    1.02
     celles
    1.02
     fourrure
    0.99
    ihr
    0.99
     neutre
    0.97
     féd
    0.97
     fréqu
    0.97
    Activations Density 0.005%

    No Known Activations