© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 70296
    Prev
    Next
    INDEX
    Explanations

    inertia and mass

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

    This neuron is tuned to detect occurrences of “inert”-related terms (e.g. inertia, inertial, inert).

    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
     TOWER
    -0.79
     engel
    -0.78
    TestBase
    -0.75
     Phal
    -0.75
    WELCOME
    -0.73
     oba
    -0.73
     stille
    -0.72
     FILES
    -0.71
     आम
    -0.70
     koper
    -0.69
    POSITIVE LOGITS
     inertia
    4.50
    Inertia
    3.14
     inertial
    3.03
    iner
    2.80
    ertia
    2.70
     iner
    2.44
     momentum
    2.25
    惯
    2.23
    INER
    1.83
    慣
    1.81
    Activations Density 0.052%

    No Known Activations