© 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. 10-GEMMASCOPE-RES-131K
    7. 119717
    Prev
    Next
    INDEX
    Explanations

    programming code and libraries

    np_acts-logits-general · gemini-2.5-flash-lite

    code-related text, particularly C source code and system programming files with copyright notices, includes, and function definitions.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     größe
    -1.66
    🧫
    -1.58
     dokonce
    -1.56
    🪛
    -1.55
    おわりに
    -1.50
    𓂂
    -1.48
    ꈍ
    -1.45
     to
    -1.42
     fizeram
    -1.41
     nepiecieš
    -1.39
    POSITIVE LOGITS
     would
    2.08
    昧
    1.85
     only
    1.59
     had
    1.55
     went
    1.53
     one
    1.52
     five
    1.52
    كيف
    1.51
     more
    1.48
     two
    1.48
    Activations Density 0.112%

    No Known Activations