© 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. 10-GEMMASCOPE-RES-131K
    7. 102682
    Prev
    Next
    INDEX
    Explanations

    Palm Beach Florida

    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_10/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
    2
    -1.80
     "
    -1.80
    0
    -1.77
    5
    -1.75
     -
    -1.74
     ("
    -1.67
    4
    -1.56
    詳しくは
    -1.54
     الح
    -1.45
     isnt
    -1.44
    POSITIVE LOGITS
    幛
    2.08
    😝
    1.82
    🌻
    1.70
    =“
    1.68
    ?”
    1.64
    ☀️
    1.62
    (),
    1.59
    ạy
    1.55
    volts
    1.55
     \%)
    1.53
    Activations Density 0.012%

    No Known Activations