© 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. 7854
    Prev
    Next
    INDEX
    Explanations

    verbs finishing tasks

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

    The neuron activates on semantically rich content words (nouns, verbs, and adjectives) rather than on common function words.

    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
     qué
    0.42
    <unused2197>
    0.42
     hâ
    0.41
     কী
    0.41
    ஃப்
    0.40
    <unused2121>
    0.38
     Jiménez
    0.38
     Pérez
    0.37
     boîte
    0.37
    <unused2164>
    0.37
    POSITIVE LOGITS
     সাধারন
    0.61
     महिलाओ
    0.61
     ঘোষনা
    0.54
    沢山
    0.54
    ॔
    0.53
    썻
    0.53
     কারনে
    0.51
    様な
    0.50
     নির্মান
    0.48
    逹
    0.48
    Activations Density 0.893%

    No Known Activations