© 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. 59772
    Prev
    Next
    INDEX
    Explanations

    border lines and zones

    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
    港
    -0.92
    Dock
    -0.91
     dock
    -0.88
     harbour
    -0.88
     harbor
    -0.87
    ื่อ
    -0.85
    分ほど
    -0.75
     deth
    -0.75
     roundabout
    -0.74
     Dock
    -0.73
    POSITIVE LOGITS
     Ligne
    1.06
     Line
    0.95
     line
    0.95
     sensores
    0.91
     ligne
    0.89
     BUFFER
    0.88
    Line
    0.87
     zone
    0.85
    这条
    0.85
     barbed
    0.84
    Activations Density 0.019%

    No Known Activations