© 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. 59953
    Prev
    Next
    INDEX
    Explanations

    language code identification

    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
    zös
    -0.76
    efois
    -0.74
    Τι
    -0.73
     barrios
    -0.72
    Ẫ
    -0.71
    图像
    -0.71
    Geografia
    -0.70
     algal
    -0.69
     start
    -0.69
     excessive
    -0.69
    POSITIVE LOGITS
     code
    1.13
     ISO
    1.12
     codes
    1.02
    ovac
    0.99
    code
    0.97
     códigos
    0.97
    Code
    0.93
     detection
    0.90
    codes
    0.87
    Codes
    0.86
    Activations Density 0.005%

    No Known Activations