© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 91928
    Prev
    Next
    INDEX
    Explanations

    chain breaker tool

    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
    📈
    -0.82
     Secara
    -0.80
    kete
    -0.75
    成長
    -0.73
    intégration
    -0.72
    entière
    -0.72
    ༅
    -0.72
     względem
    -0.71
    ͧ
    -0.71
    百科
    -0.70
    POSITIVE LOGITS
     tool
    2.25
     tools
    1.77
    工具
    1.71
    tool
    1.62
     Tool
    1.47
     herramienta
    1.37
    tools
    1.34
    Tool
    1.34
    pull
    1.34
     pull
    1.27
    Activations Density 0.035%

    No Known Activations