© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 66132
    Prev
    Next
    INDEX
    Explanations

    LaTeX and XML namespaces

    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
     immense
    -1.47
     strona
    -1.46
     România
    -1.44
     najleps
    -1.42
     ſen
    -1.40
    yyj
    -1.37
     Anreg
    -1.37
     чрезвы
    -1.36
    rmk
    -1.36
    ſter
    -1.35
    POSITIVE LOGITS
     more
    2.22
     like
    2.09
     not
    1.86
    zegovina
    1.77
     after
    1.77
     what
    1.65
     both
    1.62
     does
    1.60
     only
    1.58
     see
    1.54
    Activations Density 0.007%

    No Known Activations