© 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. 9369
    Prev
    Next
    INDEX
    Explanations

    days and weather

    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
    ίη
    -1.07
    ḫ
    -1.02
     lieve
    -0.98
    itado
    -0.96
    gulier
    -0.96
    ремонт
    -0.96
     åren
    -0.96
     henne
    -0.95
     honda
    -0.95
    cillors
    -0.94
    POSITIVE LOGITS
     people
    1.16
     temperature
    1.07
     conditions
    1.02
     więc
    1.01
     temperatures
    0.99
     my
    0.96
     trotzdem
    0.95
     atmosphere
    0.94
    Поэтому
    0.94
     we
    0.93
    Activations Density 0.030%

    No Known Activations