© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 749
    Prev
    Next
    INDEX
    Explanations

    coding components and services

    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
     The
    -2.16
     Of
    -2.02
    lccn
    -1.91
     As
    -1.78
    崴
    -1.76
     to
    -1.72
     gleaming
    -1.70
     since
    -1.70
    珺
    -1.66
     OF
    -1.63
    POSITIVE LOGITS
     japonais
    1.84
     Théâtre
    1.70
    那些
    1.69
     Sofía
    1.68
    Seems
    1.68
     chansons
    1.66
    0
    1.66
    我們
    1.66
     stiller
    1.66
     mavi
    1.66
    Activations Density 0.002%

    No Known Activations