© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-12B
    3. 31-GEMMASCOPE-2-RES-16K
    4. 13252
    Prev
    Next
    INDEX
    Explanations

    `</h1>`

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

    This neuron activates on standalone title or heading tokens—especially capitalized nouns used as section or article titles.

    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
    ]]></
    0.75
    ))]
    0.72
    रोक्त
    0.68
    墉
    0.63
    "]);
    0.63
     Joe
    0.61
     розташо
    0.61
     joe
    0.60
    isement
    0.59
     Bhavan
    0.58
    POSITIVE LOGITS
    </h1>
    1.98
    ).}
    1.19
    </th>
    1.17
    $.}
    1.16
    )}.
    1.11
    $}
    1.10
    ")}
    1.09
    ')}
    1.07
    <h1>
    1.05
    </caption>
    1.04
    Activations Density 0.003%

    No Known Activations