© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 5098
    Prev
    Next
    INDEX
    Explanations

    liquid

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

    This neuron detects mentions of cyanoacrylate-based adhesives (e.g. “CA glue,” “super glue,” etc.).

    oai_token-act-pair · o4-mini
    Triggered 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
    Negative Logits
    횡
    0.65
    娩
    0.62
     Rajya
    0.59
    쌓
    0.58
    横
    0.57
    ambuco
    0.55
    橫
    0.55
    etva
    0.55
    ču
    0.54
     transversely
    0.54
    POSITIVE LOGITS
     liquid
    1.59
    液体
    1.53
     spray
    1.52
     formulations
    1.48
     sprays
    1.48
     Liquid
    1.42
    液
    1.42
    Liquid
    1.41
     liquids
    1.38
     Spray
    1.36
    Activations Density 1.390%

    No Known Activations