© 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. 128420
    Prev
    Next
    INDEX
    Explanations

    African presidents, programming contexts

    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
    tický
    -1.08
     instead
    -0.88
     MAL
    -0.87
    Nc
    -0.85
    라고
    -0.84
    ズム
    -0.84
    大声
    -0.83
     DH
    -0.82
     MAR
    -0.81
    عى
    -0.81
    POSITIVE LOGITS
     Enero
    1.05
    luß
    1.04
     trama
    1.02
     NEGRO
    1.00
     BAKER
    1.00
     exerted
    0.98
     inoxid
    0.98
     subsidi
    0.96
     ought
    0.96
    Ihre
    0.92
    Activations Density 0.000%

    No Known Activations