© 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. 119798
    Prev
    Next
    INDEX
    Explanations

    quoted speech or statement

    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
    )),
    -1.43
    yeur
    -1.42
    According
    -1.40
     dianteiro
    -1.35
     作り方
    -1.32
    Significado
    -1.30
    ària
    -1.28
    Menurut
    -1.28
     {};
    -1.27
     DialogResult
    -1.25
    POSITIVE LOGITS
     "
    1.98
     then
    1.92
     “
    1.64
     although
    1.52
     overall
    1.48
     '
    1.41
     products
    1.41
     inauguración
    1.41
     which
    1.39
     because
    1.38
    Activations Density 0.043%

    No Known Activations