© 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. 10-GEMMASCOPE-RES-131K
    7. 129027
    Prev
    Next
    INDEX
    Explanations

    quality control or QC

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

    The neuron fires on occurrences of the two-letter sequence “QC” (often standing alone as the token “QC”).

    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
    ).
    -3.58
    इटम
    -3.14
     Then
    -2.89
     That
    -2.83
     If
    -2.63
    は
    -2.42
     Not
    -2.42
     There
    -2.41
     For
    -2.41
     They
    -2.39
    POSITIVE LOGITS
    and
    2.91
    9
    2.63
    蜩
    2.59
    you
    2.53
    4
    2.48
    even
    2.48
    也很
    2.48
    7
    2.45
    跑到
    2.41
    6
    2.41
    Activations Density 0.002%

    No Known Activations