© 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-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 43
    Prev
    Next
    INDEX
    Explanations

    Q-words and Q-starting sequences

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

    The neuron strongly activates on tokens that are standalone or prefixed “Q” alphanumeric codes (e.g. product or currency identifiers beginning with “Q”).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     verme
    0.55
     ipak
    0.52
    ◤
    0.52
     Gop
    0.50
    ائب
    0.50
    клон
    0.50
     konst
    0.49
     unglaublich
    0.49
    च्च
    0.49
     Darstellung
    0.49
    POSITIVE LOGITS
     q
    0.76
     Q
    0.70
     Qc
    0.68
    Ｑ
    0.66
     Qd
    0.66
     Qe
    0.65
    Qs
    0.61
     QA
    0.61
     QC
    0.61
     qc
    0.59
    Activations Density 0.354%

    No Known Activations