© 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. 22-GEMMASCOPE-RES-131K
    7. 14036
    Prev
    Next
    INDEX
    Explanations

    database join operations

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

    The neuron activates on occurrences of the keyword “join” (i.e. SQL JOIN operations).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     This
    -2.44
     هذا
    -2.34
    隹
    -2.31
    .
    -2.30
     این
    -2.30
     important
    -2.30
    this
    -2.25
    ꒥
    -2.23
    忖
    -2.23
     इस
    -2.23
    POSITIVE LOGITS
    5
    3.33
    2
    2.78
    ごちそう
    2.73
    在她
    2.63
    ご馳走
    2.61
    1
    2.50
    タクシー
    2.47
    已经在
    2.42
    9
    2.34
    她和
    2.31
    Activations Density 0.011%

    No Known Activations