© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 73247
    Prev
    Next
    INDEX
    Explanations

    assignments or indexed items

    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_22/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
    そのため
    -0.98
     Russian
    -0.95
    *}{
    -0.89
     after
    -0.89
    vantaged
    -0.86
     wiring
    -0.86
    镌
    -0.85
     minde
    -0.84
    你看
    -0.83
     interesting
    -0.82
    POSITIVE LOGITS
     cinquante
    0.94
    醸
    0.92
     gucci
    0.91
     levering
    0.90
     SOU
    0.89
     kapcs
    0.86
     spécialisé
    0.84
     Quoi
    0.84
    Decrypt
    0.84
     spécialement
    0.82
    Activations Density 0.010%

    No Known Activations