© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 3210
    Prev
    Next
    INDEX
    Explanations

    The neuron detects list‐item enumerators—standalone numbers (and similar markers) that label ordered list entries.

    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
    ":[
    0.67
    ?".
    0.67
     latter
    0.64
    "></
    0.64
    {}".
    0.63
     फिर
    0.61
    "};
    0.61
    ",[
    0.60
     again
    0.60
    </h1>
    0.58
    POSITIVE LOGITS
    )
    2.83
    ）
    2.09
    .)
    2.08
    ))
    1.99
     )
    1.84
    )...
    1.82
    ),
    1.81
    )\
    1.80
    -)
    1.80
    ())
    1.76
    Activations Density 0.125%

    No Known Activations