© 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. 39215
    Prev
    Next
    INDEX
    Explanations

    sports teams like Tigers

    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
    “
    -3.53
    袮
    -2.92
    '
    -2.59
    他们在
    -2.55
    ۔
    -2.48
     tidak
    -2.45
    l
    -2.42
    '].
    -2.39
     usato
    -2.36
    ཫ
    -2.31
    POSITIVE LOGITS
    いれば
    3.02
    刖
    2.75
    .
    2.73
     abbildung
    2.73
     the
    2.55
     größ
    2.53
     podem
    2.48
    ぢ
    2.42
    értelmű
    2.38
     complicada
    2.38
    Activations Density 0.004%

    No Known Activations