© 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. 60459
    Prev
    Next
    INDEX
    Explanations

    HTML form generation code

    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
    onet
    -0.88
    ueltos
    -0.83
    ி
    -0.79
     Envío
    -0.74
     home
    -0.73
     Mauritania
    -0.73
    uker
    -0.73
    Datepicker
    -0.73
     WARRANT
    -0.73
    heb
    -0.73
    POSITIVE LOGITS
     Form
    1.24
     form
    1.09
     forms
    1.01
     HTML
    1.00
    Form
    0.90
     Html
    0.90
     FORM
    0.88
    form
    0.87
    Html
    0.86
    close
    0.82
    Activations Density 0.011%

    No Known Activations