© 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. 59929
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     our
    -1.80
     of
    -1.66
     legislat
    -1.42
    ?
    -1.38
     -
    -1.36
     nuestro
    -1.35
     nuestras
    -1.34
    バーガー
    -1.27
     that
    -1.26
     =
    -1.24
    POSITIVE LOGITS
     heilig
    1.67
     spannend
    1.58
     gese
    1.49
     geheim
    1.47
     heilige
    1.46
     technisch
    1.46
     bedankt
    1.43
     nette
    1.42
     eventful
    1.41
     stoff
    1.38
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.