© 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. 128151
    Prev
    Next
    INDEX
    Explanations

    This neuron fires on the “id” token (and its closing parenthesis) when it appears as part of a PRIMARY KEY declaration in SQL DDL statements.

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

    Keywords for SQL, code, and specific entities

    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
    нула
    -1.05
     esfuerzan
    -1.00
     ecosistema
    -0.99
     fenomen
    -0.98
     alkoh
    -0.96
     crédit
    -0.96
     ferien
    -0.94
    nuk
    -0.94
     Teknik
    -0.94
    mehr
    -0.94
    POSITIVE LOGITS
     Rückseite
    0.95
    ところに
    0.93
     ['./
    0.93
    These
    0.92
     will
    0.90
     ruchu
    0.90
    どうなる
    0.89
    ietal
    0.89
     and
    0.88
     ,
    0.87
    Activations Density 0.000%

    No Known Activations