© 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-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 43266
    Prev
    Next
    INDEX
    Explanations

    InnoDB database engine

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

    The neuron detects mixed-case “camel‐case” letter sequences within words (e.g. lacZ, InnoDB).

    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
    viembre
    -2.72
    渽
    -2.59
     แต่
    -2.47
    。『
    -2.45
    ꦫ
    -2.34
    ㈮
    -2.31
    的
    -2.31
    亙
    -2.30
    quelize
    -2.28
     også
    -2.25
    POSITIVE LOGITS
     he
    3.56
     was
    2.89
    “
    2.38
    ?"
    2.33
     той
    2.20
    {
    2.19
     две
    2.14
     será
    2.13
     sont
    2.09
     И
    2.06
    Activations Density 0.000%

    No Known Activations