© 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. 68184
    Prev
    Next
    INDEX
    Explanations

    Transactions on

    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
     only
    -2.14
    _
    -2.09
     two
    -2.06
     one
    -2.03
     should
    -1.94
     will
    -1.91
    g
    -1.80
     three
    -1.74
     if
    -1.73
     start
    -1.73
    POSITIVE LOGITS
    卝
    1.94
    ⩤
    1.92
    
    1.83
    氿
    1.77
    
    1.76
    موقع
    1.75
    カッコいい
    1.73
    の状態
    1.70
     リフォーム
    1.65
    腘
    1.62
    Activations Density 0.000%

    No Known Activations