© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 63933
    Prev
    Next
    INDEX
    Explanations

    mechanical stress and strain

    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
    ISTICS
    -0.77
    木坂
    -0.76
     ionization
    -0.76
    کوراسیون
    -0.76
    icians
    -0.74
    ivers
    -0.73
     Secre
    -0.72
    щита
    -0.71
    mekte
    -0.71
    >(</
    -0.71
    POSITIVE LOGITS
     stress
    2.45
     stresses
    2.31
     Stress
    1.97
    stress
    1.86
    Stress
    1.79
     stressed
    1.63
    stressed
    1.48
     strains
    1.41
     strain
    1.41
     stressors
    1.31
    Activations Density 0.043%

    No Known Activations