© 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. 99337
    Prev
    Next
    INDEX
    Explanations

    offers something

    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
    ſſen
    -3.47
     erhi
    -3.16
    鵙
    -3.13
    i
    -3.13
     they
    -3.03
    ༵
    -2.94
    螄
    -2.88
    ي
    -2.77
     kapture
    -2.75
    
    -2.73
    POSITIVE LOGITS
     They
    3.47
     If
    3.39
     There
    3.14
     Sadly
    2.91
     ….
    2.89
    ….
    2.83
    
    2.81
    辚
    2.81
     Additionally
    2.77
    
    2.72
    Activations Density 0.020%

    No Known Activations