© 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. 1001
    Prev
    Next
    INDEX
    Explanations

    The neuron fires strongly on words that appear inside punctuation—especially quoted terms or hyphen-joined compounds.

    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
    .`);
    0.93
    .);
    0.91
    ...");
    0.85
     {});
    0.82
    !"));
    0.80
    ...');
    0.79
    !");
    0.77
    ?");
    0.77
    ...).
    0.75
    …).
    0.75
    POSITIVE LOGITS
    ”
    1.45
    」
    1.36
    』
    1.10
    ’’
    1.08
    »
    1.05
    ''
    1.04
    ˮ
    1.01
    )
    0.98
    ()
    0.98
    "'
    0.98
    Activations Density 0.993%

    No Known Activations