© 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. 10-GEMMASCOPE-RES-131K
    7. 555
    Prev
    Next
    INDEX
    Explanations

    food sauce or Sauce publication

    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
    n
    -3.13
    *
    -2.97
    [
    -2.58
     That
    -2.44
     nasty
    -2.41
     While
    -2.36
    /
    -2.27
    as
    -2.25
    
    -2.23
     cumbersome
    -2.22
    POSITIVE LOGITS
    崀
    2.78
    镚
    2.78
     fatores
    2.56
    蓠
    2.55
    ли
    2.52
    
    2.50
     wist
    2.48
    锖
    2.47
     criada
    2.41
    ᨉ
    2.41
    Activations Density 0.012%

    No Known Activations