© 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. 83732
    Prev
    Next
    INDEX
    Explanations

    introductions and headings

    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
     Beb
    -0.75
    স্ট
    -0.72
     Nuc
    -0.72
     iridescent
    -0.70
    ✊
    -0.70
    发动机
    -0.69
    RelativeLayout
    -0.68
     chemo
    -0.68
     masts
    -0.68
    ودة
    -0.67
    POSITIVE LOGITS
     Conditioning
    0.89
    wnie
    0.85
     latent
    0.85
     disques
    0.83
    pixels
    0.82
     conditioning
    0.77
    textStyle
    0.77
     khóa
    0.77
    merk
    0.76
     onDestroy
    0.75
    Activations Density 0.017%

    No Known Activations