© 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. 34-GEMMASCOPE-RES-131K
    7. 75931
    Prev
    Next
    INDEX
    Explanations

    html video

    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_34/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
     печа
    -0.87
    clyde
    -0.81
    mathfrak
    -0.79
     เด
    -0.77
    ascii
    -0.77
     DeFi
    -0.74
     diplomatic
    -0.74
    冠軍
    -0.73
     przed
    -0.73
    AZIONI
    -0.72
    POSITIVE LOGITS
     video
    3.56
     videos
    2.80
     Video
    2.78
    video
    2.64
    Video
    2.63
    videos
    2.17
     Videos
    2.11
    Videos
    2.05
     видео
    2.05
     vidéo
    2.00
    Activations Density 0.161%

    No Known Activations