© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 9350
    Prev
    Next
    INDEX
    Explanations

    quotation mark and ending punctuation

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

    The neuron detects individual words that are enclosed in quotation marks.

    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
     এবং
    1.13
     and
    1.09
     और
    1.05
    and
    1.01
     и
    1.00
    和
    0.95
     અને
    0.92
     و
    0.89
    以及
    0.88
    力和
    0.86
    POSITIVE LOGITS
    」
    2.16
    ”
    1.94
    ˮ
    1.74
    」、
    1.62
    ”（
    1.52
    ”)
    1.50
    ”—
    1.50
    ”?
    1.49
    ”(
    1.48
    ")
    1.46
    Activations Density 0.000%

    No Known Activations