© 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. 119007
    Prev
    Next
    INDEX
    Explanations

    CGRect and size dimensions

    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
    horizontalLayout
    -0.93
    チュア
    -0.81
    leep
    -0.78
    -[
    -0.78
     thr
    -0.77
     ["
    -0.76
    (['
    -0.75
    =("
    -0.75
     ViewHolder
    -0.75
     [
    -0.75
    POSITIVE LOGITS
    origin
    1.13
     origin
    1.02
     CGRect
    0.87
     Beaches
    0.87
    size
    0.85
     size
    0.82
     origins
    0.82
    Origin
    0.79
     maxx
    0.79
     YY
    0.76
    Activations Density 0.015%

    No Known Activations