© 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. 34-GEMMASCOPE-RES-131K
    7. 49088
    Prev
    Next
    INDEX
    Explanations

    photometry and completeness tests

    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_34/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
     interesse
    -0.78
     marinated
    -0.75
    oward
    -0.73
    逅
    -0.73
     monoch
    -0.72
    wara
    -0.72
    heng
    -0.72
     Davide
    -0.70
     Equality
    -0.69
    ebrow
    -0.69
    POSITIVE LOGITS
     PSF
    0.79
    structural
    0.77
    tractor
    0.76
    mylist
    0.74
    traction
    0.72
    SQLite
    0.72
     BACKGROUND
    0.69
     flux
    0.69
     Zer
    0.68
     Nit
    0.68
    Activations Density 0.019%

    No Known Activations