© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 11922
    Prev
    Next
    INDEX
    Explanations

    superpower

    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
    toppers
    -1.72
    onOptions
    -1.71
    '
    -1.69
     about
    -1.66
     depositphotos
    -1.62
    lblNewLabel
    -1.59
    。"
    -1.49
     スタンド
    -1.49
    blurRadius
    -1.47
     argento
    -1.45
    POSITIVE LOGITS
    E
    2.16
     are
    1.76
     weary
    1.63
     verschiedene
    1.60
    出了一
    1.55
     powers
    1.47
     izquierdo
    1.46
     kurz
    1.46
     saben
    1.45
    一些
    1.42
    Activations Density 0.009%

    No Known Activations