© 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. 99606
    Prev
    Next
    INDEX
    Explanations

    words starting with "со"

    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
    .
    -2.89
     következő
    -2.78
    
    -2.64
     sorprender
    -2.59
    鈁
    -2.50
     vorigen
    -2.47
     beeindruck
    -2.38
    )”
    -2.34
     besonder
    -2.34
    pertino
    -2.33
    POSITIVE LOGITS
     It
    3.09
     was
    2.89
    a
    2.58
    enablog
    2.56
     enchanting
    2.56
    e
    2.48
    ".
    2.47
    𓐍
    2.36
    鰨
    2.33
     alarming
    2.30
    Activations Density 0.001%

    No Known Activations