© 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. 33565
    Prev
    Next
    INDEX
    Explanations

    Java methods and code structures

    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
    χή
    -0.79
    Salem
    -0.79
    ialak
    -0.76
    èze
    -0.74
    fgaben
    -0.74
     aplicado
    -0.72
    Neutral
    -0.71
    Jika
    -0.71
     Salem
    -0.69
    rassed
    -0.69
    POSITIVE LOGITS
     service
    1.37
    doGet
    1.09
    handleRequest
    1.05
    บริการ
    1.05
     doGet
    1.03
    service
    1.00
     SERVICE
    0.89
    Responding
    0.83
    服务
    0.83
    doPost
    0.81
    Activations Density 0.006%

    No Known Activations