© 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. 6733
    Prev
    Next
    INDEX
    Explanations

    register, instruction, or status check

    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
     obfusc
    -0.75
     közel
    -0.73
    RSpec
    -0.72
    糠
    -0.71
     IDE
    -0.71
    тел
    -0.70
    Texto
    -0.69
    lerden
    -0.69
    ější
    -0.68
    DUE
    -0.68
    POSITIVE LOGITS
     Address
    0.92
     addresses
    0.88
    Address
    0.87
     Memory
    0.83
     PROVISIONS
    0.82
     addressed
    0.78
    地址
    0.78
     قوات
    0.77
    アドレス
    0.77
    ADDRESS
    0.76
    Activations Density 0.021%

    No Known Activations