© 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. 28208
    Prev
    Next
    INDEX
    Explanations

    duration and time relationships

    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
     previously
    -1.21
    撮影
    -1.10
     radiador
    -1.09
     فره
    -0.99
    ThroughAttribute
    -0.98
    Capítulo
    -0.98
     препарат
    -0.98
     normally
    -0.98
    Zdra
    -0.95
     network
    -0.94
    POSITIVE LOGITS
     years
    1.56
     decade
    1.23
     decades
    1.22
     America
    1.10
     year
    1.08
     chré
    1.06
     religieuses
    1.05
    ních
    1.02
    getYear
    1.02
     latach
    1.02
    Activations Density 0.039%

    No Known Activations