© 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. 22-GEMMASCOPE-RES-131K
    7. 11511
    Prev
    Next
    INDEX
    Explanations

    bundle exec, bundle install, bundle of

    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
    '
    -3.09
    
    -2.78
    an
    -2.56
     myriad
    -2.55
     wonderfully
    -2.45
     sturdy
    -2.28
    el
    -2.28
    il
    -2.27
     hordes
    -2.25
     представителей
    -2.23
    POSITIVE LOGITS
    Shortly
    2.42
    Every
    2.41
    These
    2.39
    䉴
    2.38
     sparkly
    2.33
     exquisitely
    2.31
     indicating
    2.31
    Following
    2.28
     sooooo
    2.23
     Because
    2.22
    Activations Density 0.009%

    No Known Activations