© 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. 99048
    Prev
    Next
    INDEX
    Explanations

    URL navigation

    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
     ネックレス
    -0.84
    ierter
    -0.78
    öp
    -0.77
    liste
    -0.76
     ブレスレット
    -0.75
    
    -0.74
    ራ
    -0.74
    choss
    -0.72
     Ciao
    -0.72
     gustaría
    -0.72
    POSITIVE LOGITS
     url
    1.41
     visit
    1.27
     URL
    1.22
     visited
    1.12
     opening
    1.10
    Url
    1.09
     goTo
    1.01
     baseUrl
    1.01
     wait
    0.99
    visit
    0.99
    Activations Density 0.010%

    No Known Activations