© 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. 89975
    Prev
    Next
    INDEX
    Explanations

    point bending, through truss, unit restorations

    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
    ޭ
    -0.78
    manes
    -0.75
     conical
    -0.75
    সূত্র
    -0.72
     Saffron
    -0.72
     構造
    -0.71
    tubo
    -0.71
    rugby
    -0.67
     编
    -0.66
    elton
    -0.66
    POSITIVE LOGITS
     beam
    1.18
     bending
    1.16
     flex
    1.15
     Flex
    1.08
     span
    1.04
     sagging
    1.01
    Beam
    1.00
     Bending
    1.00
     deflection
    0.98
    挠
    0.97
    Activations Density 0.022%

    No Known Activations