© 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. 11089
    Prev
    Next
    INDEX
    Explanations

    in quotation marks

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

    This neuron detects words that occur immediately inside quotation marks, especially the first few tokens after an opening quote.

    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
     "
    1.11
     “
    0.93
     ,
    0.88
     ("
    0.85
    :
    0.85
     ;
    0.83
    ;
    0.83
    .*;
    0.83
     }
    0.81
     ،
    0.80
    POSITIVE LOGITS
    」
    1.74
    ”)
    1.46
    »)
    1.45
    」、
    1.45
    ”?
    1.38
    ｣
    1.38
    ˮ
    1.37
    ”（
    1.35
    ")
    1.33
    \")
    1.33
    Activations Density 0.381%

    No Known Activations