© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 129386
    Prev
    Next
    INDEX
    Explanations

    The neuron activates on the “);” sequence that terminates SQL UPDATE statements—i.e. it detects the closing parenthesis plus semicolon ending those queries.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    Q; In vitro; Commentary by; Passive election

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     Meille
    -1.20
    ≍
    -1.12
    xvii
    -1.09
    nú
    -1.08
    iramente
    -1.08
    ☿
    -1.05
    дие
    -1.03
    Quién
    -1.02
     História
    -1.02
     ilha
    -1.01
    POSITIVE LOGITS
    0
    1.12
    p
    1.05
    g
    1.05
    N
    1.05
    f
    1.05
    t
    1.04
    ith
    1.03
    z
    1.02
    u
    1.02
    可能有
    1.00
    Activations Density 0.000%

    No Known Activations