© 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. 34-GEMMASCOPE-RES-131K
    7. 118725
    Prev
    Next
    INDEX
    Explanations

    glfw window hints

    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_34/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
     Ngoài
    -0.82
     Simpsons
    -0.78
     麺
    -0.76
     Segel
    -0.76
    bés
    -0.75
     Exeter
    -0.75
     Niem
    -0.75
     Aegean
    -0.75
     Infan
    -0.73
    ália
    -0.73
    POSITIVE LOGITS
    glfw
    1.45
     GLFW
    1.44
    GLFW
    1.13
    Nevada
    1.05
     Nevada
    1.00
     Riva
    0.84
     gl
    0.82
     Window
    0.79
     CIS
    0.79
     Mackay
    0.78
    Activations Density 0.018%

    No Known Activations