© 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. 39434
    Prev
    Next
    INDEX
    Explanations

    code structure and programming constructs

    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
    資料來源
    -0.88
     خریدار
    -0.85
    ರೆ
    -0.84
     comparatively
    -0.82
    前から
    -0.79
    爍
    -0.78
    コミュニ
    -0.78
    ága
    -0.77
     матері
    -0.77
    zwi
    -0.77
    POSITIVE LOGITS
    vation
    0.96
    lasma
    0.94
    <eos>
    0.93
    继续
    0.93
    нулась
    0.92
    strator
    0.91
     ons
    0.91
    
    0.90
     heer
    0.90
    tiness
    0.90
    Activations Density 0.001%

    No Known Activations