© 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. 65392
    Prev
    Next
    INDEX
    Explanations

    List or heading phrases

    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
     Laur
    -0.77
     Lawton
    -0.73
     drow
    -0.73
     barge
    -0.70
     drowned
    -0.70
     declar
    -0.68
     ор
    -0.68
     hydroxy
    -0.68
    ))/
    -0.68
     quotient
    -0.68
    POSITIVE LOGITS
    ⌟
    0.85
    扫
    0.79
    すべき
    0.75
     Aleg
    0.73
    faf
    0.73
     Garrison
    0.69
    Fuel
    0.69
    購物
    0.69
    pository
    0.68
    Pid
    0.68
    Activations Density 0.005%

    No Known Activations