© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 20837
    Prev
    Next
    INDEX
    Explanations

    Scottish highlands and pipes

    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_10/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
     verhind
    -1.71
     nových
    -1.52
    割と
    -1.46
    還在
    -1.42
     ausein
    -1.42
     gekocht
    -1.41
    
    -1.40
    夘
    -1.40
    鸩
    -1.40
    迫力
    -1.39
    POSITIVE LOGITS
    ”,
    1.38
     ‘
    1.38
    на
    1.38
     Scottish
    1.38
     k
    1.27
     [
    1.26
    ？
    1.25
     at
    1.23
    ma
    1.21
    не
    1.21
    Activations Density 0.076%

    No Known Activations