© 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. 7810
    Prev
    Next
    INDEX
    Explanations

    declared functions, main functions

    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
     to
    -2.28
    訁
    -2.03
    髎
    -1.98
     ทั้ง
    -1.90
     jednej
    -1.79
    
    -1.76
     $^{\
    -1.74
    bbt
    -1.72
     mesmos
    -1.70
    
    -1.70
    POSITIVE LOGITS
    0
    2.61
    2
    2.13
     =
    2.03
     thirteen
    2.02
    3
    1.98
    4
    1.95
    5
    1.95
     fifteen
    1.93
     fourteen
    1.92
     sixteen
    1.91
    Activations Density 0.016%

    No Known Activations