© 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. 48996
    Prev
    Next
    INDEX
    Explanations

    web pages or sections

    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
     lisesi
    -0.82
     maioria
    -0.80
     оригі
    -0.80
     şeklinde
    -0.80
    ogyn
    -0.79
    istered
    -0.79
     kleineren
    -0.79
    ̐
    -0.78
     einigen
    -0.78
    مزید
    -0.77
    POSITIVE LOGITS
     page
    3.83
     section
    2.81
     pages
    2.72
    page
    2.45
    Page
    2.16
     webpage
    2.05
     página
    1.93
    section
    1.89
    PAGE
    1.88
    页面
    1.84
    Activations Density 0.065%

    No Known Activations