© 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. 53836
    Prev
    Next
    INDEX
    Explanations

    CSS properties and visual appearance

    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
     deviennent
    -0.89
     ſer
    -0.86
     cartons
    -0.83
    閉じ
    -0.83
    Préparation
    -0.82
    ZIONE
    -0.82
    ・)
    -0.82
     Warrington
    -0.81
    beiter
    -0.81
     vreme
    -0.81
    POSITIVE LOGITS
     outline
    1.16
    appearance
    1.05
    outline
    1.04
     focusing
    1.02
     focus
    1.01
     appearance
    1.01
     focused
    1.00
     all
    0.95
    border
    0.86
     border
    0.85
    Activations Density 0.007%

    No Known Activations