© 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. 34-GEMMASCOPE-RES-131K
    7. 48224
    Prev
    Next
    INDEX
    Explanations

    Scheme, lists, procedures

    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
    arques
    -0.78
    жте
    -0.74
    kop
    -0.70
    Kop
    -0.69
     מול
    -0.67
     расте
    -0.67
     xy
    -0.66
     frust
    -0.66
     tomo
    -0.65
     disambigu
    -0.65
    POSITIVE LOGITS
    FromArgb
    0.88
     Scheme
    0.87
     procedure
    0.86
     parmi
    0.85
     #:
    0.85
    eficent
    0.84
     Procedure
    0.83
     procedures
    0.83
    %.
    0.82
    )]{
    0.82
    Activations Density 0.042%

    No Known Activations