© 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. 39872
    Prev
    Next
    INDEX
    Explanations

    change or variable and path

    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
    읗
    -2.42
    owaniu
    -2.36
    齶
    -2.34
    ครื่อง
    -2.31
    霂
    -2.27
    
    -2.27
    鶿
    -2.25
    鷙
    -2.22
    asiswa
    -2.19
    夘
    -2.19
    POSITIVE LOGITS
    The
    2.88
    ᩠
    2.78
     you
    2.70
    How
    2.50
    闔
    2.48
     {
    2.45
    ”
    2.44
     maxim
    2.39
    ￪
    2.36
     stringent
    2.34
    Activations Density 0.001%

    No Known Activations