© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 131069
    Prev
    Next
    INDEX
    Explanations

    PHP code snippets

    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
    olá
    -0.85
     azonban
    -0.82
    อย่างไร
    -0.78
     サービス
    -0.77
    recognition
    -0.77
     PLAY
    -0.76
     vaše
    -0.75
     projector
    -0.75
     Contenido
    -0.75
    iton
    -0.74
    POSITIVE LOGITS
     {}\
    0.79
     eksp
    0.79
     mỗi
    0.78
     regroup
    0.77
     episode
    0.75
     Schie
    0.74
    每次
    0.72
     Fuß
    0.72
     emotional
    0.72
    aż
    0.72
    Activations Density 0.039%

    No Known Activations