© 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. 118833
    Prev
    Next
    INDEX
    Explanations

    making a choice for

    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
    मुख
    -1.52
     bezw
    -1.41
    hasilkan
    -1.41
     проходит
    -1.37
    uerung
    -1.37
     листья
    -1.36
     Reduces
    -1.34
    㩒
    -1.33
     $+$
    -1.33
     $+
    -1.33
    POSITIVE LOGITS
    "
    1.63
    as
    1.63
     by
    1.60
     if
    1.56
     of
    1.55
     музе
    1.50
     якщо
    1.42
    хай
    1.41
    ˖
    1.38
    酲
    1.38
    Activations Density 0.007%

    No Known Activations