© 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. 91727
    Prev
    Next
    INDEX
    Explanations

    UI layout and status 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
     linken
    -0.79
    ⠸
    -0.75
    INGREDIENTES
    -0.75
    Trichloroethane
    -0.72
    millions
    -0.72
     Greeks
    -0.71
    tcs
    -0.71
    浴び
    -0.69
     inflicting
    -0.69
    flug
    -0.69
    POSITIVE LOGITS
     header
    1.20
    StatusBar
    1.13
     keyboard
    1.06
    getStatus
    1.06
    keyboard
    1.06
    footer
    1.05
    navbar
    0.99
     Status
    0.98
     Header
    0.98
     status
    0.97
    Activations Density 0.030%

    No Known Activations