© 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. 80836
    Prev
    Next
    INDEX
    Explanations

    list comprehensions and dictionaries

    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
     will
    -1.76
     $\
    -1.51
     which
    -1.50
     =
    -1.48
     They
    -1.48
    first
    -1.48
    逦
    -1.47
    blue
    -1.45
     ${
    -1.45
     […]
    -1.44
    POSITIVE LOGITS
     poética
    1.84
    こんな感じ
    1.69
    biblioteca
    1.63
    こんな感じで
    1.63
    悭
    1.63
    何故
    1.59
    選んだ
    1.57
    OOTD
    1.57
     její
    1.55
    obstacle
    1.54
    Activations Density 0.019%

    No Known Activations