© 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. 10-GEMMASCOPE-RES-131K
    7. 41339
    Prev
    Next
    INDEX
    Explanations

    time since an event

    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_10/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
     who
    -1.53
    壅
    -1.32
     would
    -1.29
    谕
    -1.26
    ilerini
    -1.26
     larger
    -1.25
     móg
    -1.24
     bigger
    -1.23
    YOND
    -1.23
    んだろう
    -1.23
    POSITIVE LOGITS
     it
    1.88
     they
    1.80
     we
    1.71
     there
    1.41
     this
    1.35
     첫
    1.22
    避免
    1.20
     are
    1.17
    гон
    1.16
     satisfacer
    1.13
    Activations Density 0.096%

    No Known Activations