© 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. 93440
    Prev
    Next
    INDEX
    Explanations

    mechanical strength and force

    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
    SPECT
    -0.88
     取消
    -0.87
     constamment
    -0.86
    Dyn
    -0.84
     dyn
    -0.79
     exciter
    -0.78
    ሱ
    -0.77
    ゾ
    -0.77
     Merseyside
    -0.77
    vely
    -0.76
    POSITIVE LOGITS
     force
    1.43
    force
    1.25
     Force
    1.23
    Force
    1.23
     load
    1.19
     força
    1.01
     loads
    0.96
     Load
    0.96
     forces
    0.94
     torque
    0.93
    Activations Density 0.024%

    No Known Activations