© 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. 70479
    Prev
    Next
    INDEX
    Explanations

    divergence and diversification

    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
    “
    -3.41
     другие
    -2.67
     інші
    -2.59
     vorigen
    -2.59
     höchsten
    -2.45
     that
    -2.41
     impeccable
    -2.36
    …)
    -2.34
    sandalia
    -2.30
     übrigen
    -2.22
    POSITIVE LOGITS
     ſte
    2.72
    囖
    2.69
     ſta
    2.67
    尨
    2.64
     termed
    2.50
    ⚋
    2.50
     ſy
    2.47
    瞇
    2.38
    鹩
    2.36
     "
    2.31
    Activations Density 0.003%

    No Known Activations