© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 11881
    Prev
    Next
    INDEX
    Explanations

    This neuron specializes in detecting mentions of chemical or particulate contaminants (e.g., specific substances like silicates, silicon, fuel contamination).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Rhet
    0.71
     леп
    0.61
     Lectures
    0.60
    紮
    0.60
     антен
    0.59
     rhetoric
    0.59
    扎
    0.59
    aredPreferences
    0.58
     Bootcamp
    0.57
    札
    0.56
    POSITIVE LOGITS
     crankshaft
    1.20
     bearings
    1.06
     camshaft
    1.02
     lubrication
    1.01
     lubric
    1.00
     lubricating
    0.96
     piston
    0.95
     pistons
    0.89
     flywheel
    0.88
     bearing
    0.87
    Activations Density 0.283%

    No Known Activations