© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 129883
    Prev
    Next
    INDEX
    Explanations

    insurance policy types

    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
     ♂
    -1.33
     pretože
    -1.19
    owane
    -1.19
     rhein
    -1.17
     Factbook
    -1.15
     alſo
    -1.15
    ㈯
    -1.15
    釔
    -1.15
     omdat
    -1.13
     muft
    -1.11
    POSITIVE LOGITS
     how
    1.56
     Maybe
    1.44
    You
    1.43
    Maybe
    1.42
     How
    1.37
     maybe
    1.36
     What
    1.35
     or
    1.32
     This
    1.28
     then
    1.23
    Activations Density 0.049%

    No Known Activations