© 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. 70472
    Prev
    Next
    INDEX
    Explanations

    template / generic declarations

    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
     to
    -2.41
     ayrıca
    -2.13
     sentimos
    -1.98
     बजाय
    -1.95
     '
    -1.91
    地道
    -1.88
     promove
    -1.77
     ardından
    -1.74
    gige
    -1.73
    كويكب
    -1.73
    POSITIVE LOGITS
    5
    2.83
    8
    2.83
    6
    2.83
    4
    2.78
    I
    2.73
    7
    2.70
    .
    2.61
    3
    2.61
    _
    2.48
    if
    2.47
    Activations Density 0.018%

    No Known Activations