© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 102385
    Prev
    Next
    INDEX
    Explanations

    react native code

    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
    깃
    -0.93
     підприєм
    -0.82
    acceleration
    -0.79
    kram
    -0.79
     veľmi
    -0.77
    ቃ
    -0.77
     ရ
    -0.76
    똥
    -0.75
     withdraw
    -0.75
    uestion
    -0.75
    POSITIVE LOGITS
    slideUp
    0.85
     ReactDOM
    0.78
    熔
    0.75
     dra
    0.71
    zyg
    0.71
     Aston
    0.70
    ouldering
    0.70
    Esp
    0.70
     Dra
    0.69
     Electro
    0.68
    Activations Density 0.015%

    No Known Activations