© 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. 83437
    Prev
    Next
    INDEX
    Explanations

    html element creation and javascript

    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
    PageModule
    -0.88
     timeType
    -0.88
     behalten
    -0.77
     sorprendente
    -0.76
    膵
    -0.74
     interdependent
    -0.72
    )}(\
    -0.71
     покри
    -0.71
     получается
    -0.70
    teclado
    -0.70
    POSITIVE LOGITS
    appendChild
    1.40
     div
    1.35
    div
    1.32
    Div
    1.23
     DIV
    1.16
    span
    1.15
    idiv
    1.14
    DIV
    1.12
     paragraph
    1.11
     node
    1.07
    Activations Density 0.014%

    No Known Activations