© 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. 94176
    Prev
    Next
    INDEX
    Explanations

    XML/HTML attributes and declarations

    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
     Bigelow
    -0.75
     cocaína
    -0.69
     Rwanda
    -0.64
    柔
    -0.63
    antee
    -0.63
     meditation
    -0.63
    Abuse
    -0.63
     Waugh
    -0.62
    Ave
    -0.62
     ^{-
    -0.62
    POSITIVE LOGITS
     addition
    0.71
    িয়া
    0.70
     quasi
    0.68
    あるので
    0.68
    것은
    0.68
    ！】
    0.67
     additions
    0.66
    𝟒
    0.66
    сль
    0.65
    URBAN
    0.64
    Activations Density 0.055%

    No Known Activations