© 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. 115850
    Prev
    Next
    INDEX
    Explanations

    balancing acts and physical balance

    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
     Spanyol
    -0.73
     Warte
    -0.73
    TokenNameCOMMA
    -0.71
     ২
    -0.71
     regolare
    -0.70
    Liefs
    -0.69
    ultas
    -0.69
    ctional
    -0.68
     rumahnya
    -0.68
    sapp
    -0.67
    POSITIVE LOGITS
     balancing
    2.64
     Balancing
    2.47
    balancing
    2.36
    Balancing
    2.33
     balance
    2.03
     Balance
    1.99
     балан
    1.97
    balance
    1.97
    Balance
    1.96
     BALANCE
    1.86
    Activations Density 0.031%

    No Known Activations