© 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. 84325
    Prev
    Next
    INDEX
    Explanations

    code instantiation and programming constructs

    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
     Canoe
    -0.73
     RESET
    -0.68
     Automotive
    -0.68
    Gum
    -0.66
    Reset
    -0.66
     Urbano
    -0.65
     Orr
    -0.65
     スタンダード
    -0.65
     seconded
    -0.65
    Barber
    -0.65
    POSITIVE LOGITS
    newNode
    0.71
    imshow
    0.71
    γραφία
    0.71
    salary
    0.71
    zości
    0.71
    श्चित
    0.68
     salary
    0.68
     新
    0.68
    strftime
    0.67
    sterna
    0.66
    Activations Density 0.050%

    No Known Activations