© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 57399
    Prev
    Next
    INDEX
    Explanations

    q or q followed by various characters

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

    The neuron fires on standalone “q” tokens (often as the Qt‐style “Q” prefix or in names like q_atomic_increment), i.e. it spotlights identifiers beginning with the letter “q.”

    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
    ↵
    -4.22
    </h3>
    -3.19
    </u>
    -3.00
    </strong>
    -2.98
     و
    -2.97
    with
    -2.69
    You
    -2.64
     kleinen
    -2.64
    Several
    -2.64
    </i>
    -2.55
    POSITIVE LOGITS
    埽
    3.17
     was
    3.00
    ⃑
    2.80
    휀
    2.78
    一旁
    2.73
    🫅
    2.73
    🧌
    2.70
    饪
    2.67
    "—
    2.67
    
    2.66
    Activations Density 0.010%

    No Known Activations