© 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. 57778
    Prev
    Next
    INDEX
    Explanations

    css measurement units and viewport values

    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
    KAS
    -0.88
    rond
    -0.85
    etar
    -0.83
     paris
    -0.80
     egent
    -0.78
     firebaseConfig
    -0.78
     MAPS
    -0.77
     チップ
    -0.76
     ارتباط
    -0.75
     Robo
    -0.75
    POSITIVE LOGITS
    vh
    0.97
    vw
    0.95
     section
    0.93
    vmin
    0.93
     Section
    0.82
     viewport
    0.82
    section
    0.81
    Від
    0.78
    Vw
    0.77
     clamping
    0.76
    Activations Density 0.023%

    No Known Activations