© 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. 65543
    Prev
    Next
    INDEX
    Explanations

    popular

    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
     I
    -1.68
     P
    -1.48
     a
    -1.45
     L
    -1.39
     A
    -1.33
     l
    -1.33
     some
    -1.32
     “
    -1.31
     ra
    -1.30
     c
    -1.28
    POSITIVE LOGITS
    人気の
    1.88
    popular
    1.71
    Popular
    1.63
    人気
    1.58
     POPULAR
    1.48
    月に
    1.45
    ଅ
    1.44
     popular
    1.42
     popolare
    1.41
     córdoba
    1.38
    Activations Density 0.054%

    No Known Activations