© 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. 109382
    Prev
    Next
    INDEX
    Explanations

    HTML doctype 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
    строи
    -0.72
    ін
    -0.70
     onboard
    -0.69
    anganan
    -0.68
     Knox
    -0.68
    荼
    -0.68
     تری
    -0.68
    ligg
    -0.67
    deme
    -0.66
     Belvedere
    -0.65
    POSITIVE LOGITS
    enter
    0.73
     とき
    0.72
     Azo
    0.68
    iable
    0.66
    ほう
    0.63
    aio
    0.63
     onset
    0.63
     enter
    0.63
    Saxon
    0.62
    齦
    0.62
    Activations Density 0.078%

    No Known Activations