© 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. 73323
    Prev
    Next
    INDEX
    Explanations

    sizes and quantities

    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
    asked
    -1.16
    surprised
    -1.13
    asking
    -1.11
    appeared
    -1.09
    わが
    -1.09
    Hvordan
    -1.09
    updating
    -1.07
    respected
    -1.07
    我一直
    -1.06
    advised
    -1.06
    POSITIVE LOGITS
    time
    1.20
     maart
    1.15
     version
    1.11
    ٧
    1.11
     ))
    1.03
    version
    1.02
    гласно
    1.02
    usen
    0.99
    most
    0.98
     believer
    0.98
    Activations Density 0.054%

    No Known Activations