© 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. 82298
    Prev
    Next
    INDEX
    Explanations

    web services and SOAP

    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
     Contamination
    -0.85
    公共
    -0.85
    dirond
    -0.82
     INSTANCE
    -0.80
     saja
    -0.80
     Blush
    -0.79
    ppa
    -0.79
    źdz
    -0.78
    $^{\
    -0.77
     HAMILTON
    -0.77
    POSITIVE LOGITS
     Ве
    0.81
     USC
    0.77
    asm
    0.74
    protoc
    0.73
     Web
    0.71
     conjugate
    0.70
     км
    0.69
    Facades
    0.69
     Chapter
    0.69
     Kram
    0.69
    Activations Density 0.016%

    No Known Activations