© 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. 99647
    Prev
    Next
    INDEX
    Explanations

    money

    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
     corrom
    -1.64
     dimost
    -1.58
     decorativa
    -1.55
     atleast
    -1.54
     silueta
    -1.53
     camuf
    -1.53
     labd
    -1.52
     refroid
    -1.50
     planific
    -1.49
     beaucoup
    -1.48
    POSITIVE LOGITS
     on
    2.72
     with
    2.64
     in
    2.59
     There
    1.96
     from
    1.93
     by
    1.86
     for
    1.84
    There
    1.61
     Interestingly
    1.58
     to
    1.57
    Activations Density 0.028%

    No Known Activations