© 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. 98830
    Prev
    Next
    INDEX
    Explanations

    disc and CD

    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
    )">
    -0.91
    chuhe
    -0.87
    Haw
    -0.77
     العمل
    -0.76
    hrte
    -0.76
     wifi
    -0.75
     lokale
    -0.75
    égique
    -0.75
     VGA
    -0.75
    naux
    -0.74
    POSITIVE LOGITS
     CD
    1.67
    CD
    1.39
     Cd
    1.02
     CDs
    0.98
     cd
    0.96
     laser
    0.95
    cd
    0.95
     digital
    0.94
     jewel
    0.94
     disc
    0.93
    Activations Density 0.048%

    No Known Activations