© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 68239
    Prev
    Next
    INDEX
    Explanations

    code imports or file paths

    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
     AtomicInteger
    -0.92
     homicidio
    -0.90
     Balkon
    -0.88
     antaranya
    -0.84
    ának
    -0.84
    ℅
    -0.84
    がある
    -0.82
     baloncesto
    -0.81
     Хи
    -0.81
    scrollView
    -0.80
    POSITIVE LOGITS
     no
    1.01
     virtually
    0.91
     and
    0.90
     although
    0.88
    (){}
    0.82
     began
    0.80
     nowhere
    0.79
    ご覧ください
    0.79
    Although
    0.79
     practically
    0.77
    Activations Density 0.028%

    No Known Activations