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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 110659
    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
    🏃
    -0.75
    yng
    -0.73
     протягом
    -0.71
     british
    -0.71
     което
    -0.70
     spanish
    -0.69
     روزانه
    -0.68
    땐
    -0.68
     snippetHide
    -0.68
     discern
    -0.68
    POSITIVE LOGITS
     Friday
    5.41
     Tuesday
    5.34
     Wednesday
    5.25
     Thursday
    5.19
     Monday
    5.19
     Saturday
    4.94
     Sunday
    4.66
    Friday
    4.00
    Thursday
    3.86
    Tuesday
    3.86
    Activations Density 0.102%

    No Known Activations