© 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. 34-GEMMASCOPE-RES-131K
    7. 109335
    Prev
    Next
    INDEX
    Explanations

    code generation and documentation

    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
     angka
    -0.90
    ACIAS
    -0.82
    onChangeText
    -0.82
     betyr
    -0.78
     stund
    -0.76
     Depression
    -0.76
     קו
    -0.75
    getLatitude
    -0.74
    ندي
    -0.74
     justifyContent
    -0.73
    POSITIVE LOGITS
    طل
    0.87
     दूस
    0.85
     celor
    0.81
     moitié
    0.80
    اله
    0.75
     économies
    0.74
     navires
    0.73
     Belarusian
    0.73
     männis
    0.72
    Fernando
    0.71
    Activations Density 0.001%

    No Known Activations