© 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. 25906
    Prev
    Next
    INDEX
    Explanations

    mechanical cell properties

    np_acts-logits-general · gemini-2.5-flash-lite

    discussions of cellular and molecular biology mechanisms, particularly involving cell structure and mechanical interactions.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The neuron selectively activates on technical biomechanical and mechanobiological terminology—especially words containing the “mechan‐/mechano‐” root referring to mechanical processes in cells.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
     paillettes
    -0.82
    webkit
    -0.79
    ionization
    -0.77
     okres
    -0.77
     contemporaine
    -0.76
    斯科
    -0.75
    raisal
    -0.73
    änger
    -0.73
    ụy
    -0.72
     televis
    -0.71
    POSITIVE LOGITS
     force
    1.29
     forces
    1.07
     kPa
    1.05
    ctomy
    1.04
     mechanical
    1.02
     mechanics
    0.96
     mechan
    0.93
     mech
    0.92
     collective
    0.91
     traction
    0.91
    Activations Density 0.165%

    No Known Activations