© 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. 22-GEMMASCOPE-RES-131K
    7. 38223
    Prev
    Next
    INDEX
    Explanations

    filenames and paths

    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
     เห
    -1.14
    trange
    -1.06
    ╗
    -1.02
    
    -0.98
    oons
    -0.98
    YR
    -0.97
     acolo
    -0.97
    readFileSync
    -0.96
    IDADES
    -0.96
    lanco
    -0.94
    POSITIVE LOGITS
    āja
    1.02
     steder
    0.99
     Einzelnen
    0.95
     locations
    0.94
    Having
    0.94
    Despite
    0.93
     it
    0.93
     onItemClick
    0.93
    ziplin
    0.92
    性质
    0.91
    Activations Density 0.029%

    No Known Activations