© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 128964
    Prev
    Next
    INDEX
    Explanations

    This neuron fires on the “id” identifier (especially in SQL DDL primary‐key or column definitions).

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

    ID, UNIQUE, Boston, Controlled, Motorcycle

    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
     when
    -1.29
     from
    -1.21
     at
    -1.11
     for
    -1.09
    aspectj
    -1.08
     to
    -1.07
     then
    -1.01
    +(\
    -1.01
     after
    -1.00
     on
    -0.98
    POSITIVE LOGITS
    錾
    1.10
     gesetzlichen
    1.08
    τη
    0.99
     nhưng
    0.97
    Gewicht
    0.93
    廡
    0.93
     però
    0.92
     INDEPENDENT
    0.91
     vorhandenen
    0.91
    そりゃ
    0.91
    Activations Density 0.002%

    No Known Activations