© 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. 7020
    Prev
    Next
    INDEX
    Explanations

    ceramic materials

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

    This neuron activates on mentions of ceramic materials (e.g. “ceramic,” “ceramics,” or ceramic-based items).

    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
     a
    -0.89
     copper
    -0.86
     péro
    -0.85
     silver
    -0.83
     série
    -0.78
     February
    -0.77
     atletas
    -0.77
    綸
    -0.77
     dessinée
    -0.76
     adapté
    -0.76
    POSITIVE LOGITS
     ceramic
    1.30
     Ceramic
    1.29
    ceramic
    1.20
     tile
    1.12
     porcelain
    1.11
    tile
    1.06
     tiles
    1.04
     Tiles
    1.04
    𝗣
    1.00
    Ceramic
    0.99
    Activations Density 0.015%

    No Known Activations