© 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. 34-GEMMASCOPE-RES-131K
    7. 48830
    Prev
    Next
    INDEX
    Explanations

    code comments, headers, html, json

    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
    かったので
    -0.71
    dup
    -0.70
     PREVIEW
    -0.70
    tioned
    -0.69
    itarias
    -0.68
     wooded
    -0.67
    OTION
    -0.65
    subpackage
    -0.64
    διά
    -0.64
     oni
    -0.64
    POSITIVE LOGITS
    ෛ
    0.74
    커
    0.65
    蟆
    0.64
     Sass
    0.63
    ந்து
    0.63
     Regulated
    0.63
    追
    0.63
    áš
    0.63
    MPEG
    0.62
    ત્ર
    0.61
    Activations Density 0.124%

    No Known Activations