© 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. 66119
    Prev
    Next
    INDEX
    Explanations

    mechanical strain and deformation

    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
     Biophys
    -0.77
    خذ
    -0.74
    österreich
    -0.72
    libur
    -0.71
    fmf
    -0.71
     addSubview
    -0.70
    nigh
    -0.70
    fcn
    -0.70
    RETRY
    -0.70
     monumentos
    -0.70
    POSITIVE LOGITS
     strain
    2.88
     strains
    2.66
     Strain
    2.44
    Strain
    2.36
    strain
    2.31
     Strains
    2.02
    strains
    1.88
     deformation
    1.73
     elongation
    1.70
     straining
    1.49
    Activations Density 0.046%

    No Known Activations