© 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. 10-GEMMASCOPE-RES-131K
    7. 130570
    Prev
    Next
    INDEX
    Explanations

    ceramic components and materials

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

    The neuron strongly responds to mentions of ceramic materials or ceramic-based components in technical descriptions.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     smlou
    -1.44
    mės
    -1.39
    騭
    -1.38
     moletom
    -1.32
     represents
    -1.28
    izarra
    -1.28
    ܜ
    -1.27
     symbolizes
    -1.25
     It
    -1.25
    énagement
    -1.23
    POSITIVE LOGITS
     of
    1.50
     astute
    1.28
    colgroup
    1.26
    stone
    1.23
    ified
    1.19
    layed
    1.18
    まず
    1.18
     ‌
    1.16
    WE
    1.14
    acid
    1.14
    Activations Density 0.076%

    No Known Activations