© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 109528
    Prev
    Next
    INDEX
    Explanations

    home related pages

    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
    poda
    -0.77
     Cinemas
    -0.72
    赳
    -0.71
    AREA
    -0.66
    ія
    -0.66
    funktion
    -0.66
    Generating
    -0.66
    🍼
    -0.65
    いただけ
    -0.65
     armed
    -0.65
    POSITIVE LOGITS
    เพื่อน
    0.70
    冲
    0.69
     Emper
    0.68
    当店
    0.68
     trăng
    0.66
     wronged
    0.64
     agony
    0.64
     khủng
    0.63
     overtook
    0.63
     sinned
    0.62
    Activations Density 0.049%

    No Known Activations