© 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. 66507
    Prev
    Next
    INDEX
    Explanations

    many injury patterns

    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
     through
    -1.90
     while
    -1.77
     While
    -1.58
     by
    -1.56
     However
    -1.53
     with
    -1.52
     because
    -1.44
     using
    -1.44
     なら
    -1.43
     it
    -1.41
    POSITIVE LOGITS
     queste
    1.31
     aujourd
    1.28
     investissements
    1.27
    finally
    1.27
     idiotic
    1.24
     santuario
    1.23
     desember
    1.23
     datter
    1.22
     ferie
    1.22
     voer
    1.21
    Activations Density 0.208%

    No Known Activations