© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 31360
    Prev
    Next
    INDEX
    Explanations

    ionic app page elements

    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
     Diarsipkan
    -0.79
    🅂
    -0.79
    ческий
    -0.69
    onacci
    -0.69
     meticulously
    -0.68
     питання
    -0.68
     Quite
    -0.68
     Sant
    -0.67
    urio
    -0.67
     extravagant
    -0.67
    POSITIVE LOGITS
    popover
    1.10
    TabPage
    1.06
    PageModule
    1.02
    Popover
    0.98
     page
    0.92
    Page
    0.90
    page
    0.88
    溉
    0.87
     pages
    0.86
     pagine
    0.86
    Activations Density 0.005%

    No Known Activations