© 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. 92459
    Prev
    Next
    INDEX
    Explanations

    code structure elements `#include`

    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
    MemoryStream
    -1.01
     extenso
    -0.88
    çados
    -0.88
    IConfiguration
    -0.87
    msleep
    -0.84
    HttpContext
    -0.83
    ★★★
    -0.83
     BufferedImage
    -0.83
     तरह
    -0.81
    ایناق
    -0.81
    POSITIVE LOGITS
    bool
    0.93
     bool
    0.91
    感じです
    0.80
    オフ
    0.79
    都有
    0.75
    const
    0.74
     считается
    0.70
    已
    0.70
    по
    0.70
     каждой
    0.69
    Activations Density 0.017%

    No Known Activations