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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 39506
    Prev
    Next
    INDEX
    Explanations

    days and schedule times

    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_22/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
    ?,?,
    -1.20
    Zubereitung
    -1.05
    chsel
    -1.05
    uccess
    -1.02
     cuánto
    -1.02
    *************/
    -1.02
    靑
    -1.01
    сыз
    -1.00
     cotone
    -0.98
    靄
    -0.98
    POSITIVE LOGITS
     Saturday
    1.41
     Friday
    1.23
     Thursday
    1.20
     
    1.17
     April
    1.14
     Sunday
    1.13
     Wednesday
    1.13
     Monday
    1.07
     Tuesday
    1.05
     today
    1.00
    Activations Density 0.007%

    No Known Activations