© 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. 769
    Prev
    Next
    INDEX
    Explanations

    javascript async programming concepts

    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
     of
    -1.59
     to
    -1.25
     qualche
    -1.23
     outras
    -1.23
     blev
    -1.23
     altre
    -1.18
     andere
    -1.16
    -1.16
     Bahkan
    -1.16
     bahkan
    -1.16
    POSITIVE LOGITS
     profondeur
    1.17
     două
    1.17
     two
    1.16
    合計
    1.13
    ộm
    1.11
    räge
    1.08
     kleuren
    1.08
    Leo
    1.06
     evitar
    1.05
     herinner
    1.04
    Activations Density 0.205%

    No Known Activations