© 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. 107607
    Prev
    Next
    INDEX
    Explanations

    left navigation menus

    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
    strconv
    -0.92
    DialogComponent
    -0.77
     mengingatkan
    -0.77
    bucha
    -0.76
    outube
    -0.76
    caire
    -0.75
    estero
    -0.74
     escalada
    -0.74
    ongeza
    -0.74
    FormComponent
    -0.73
    POSITIVE LOGITS
     menu
    3.00
     navigation
    2.63
     sidebar
    2.55
    menu
    2.36
     side
    2.30
     left
    2.30
    Menu
    2.25
     nav
    2.13
    nav
    2.09
     menus
    2.09
    Activations Density 0.114%

    No Known Activations