© 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. 14142
    Prev
    Next
    INDEX
    Explanations

    Facial movements, Andrew Sullivan, life insurance

    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
    bánh
    -0.94
    ConverterFactory
    -0.92
     Pièces
    -0.92
    vska
    -0.90
     năng
    -0.90
    cencia
    -0.87
     adalah
    -0.87
    AnchorStyles
    -0.87
     disminuir
    -0.85
    laß
    -0.85
    POSITIVE LOGITS
    ories
    0.98
    0.90
    Mange
    0.88
    iLocal
    0.87
    Look
    0.86
    でて
    0.85
    わかります
    0.84
     neoliber
    0.83
     ず
    0.82
     उन्ह
    0.81
    Activations Density 0.001%
    No Known Activations