© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 15721
    Prev
    Next
    INDEX
    Explanations

    size and length of text

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

    This neuron is specialized to pick up numeric strings in bibliographic or publication metadata—years, page counts, edition and ISBN–style numbers, and similar digit‐heavy identifiers.

    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
     एडिशन
    0.59
     Изда
    0.55
     هد
    0.54
     книги
    0.52
    كتب
    0.52
     писатель
    0.51
    ѣ
    0.51
    远的
    0.51
    ения
    0.50
    確立
    0.50
    POSITIVE LOGITS
     publicités
    0.57
     figsize
    0.56
     densité
    0.56
     thickly
    0.55
     densely
    0.55
     densidad
    0.55
    ść
    0.54
     dense
    0.54
     সিং
    0.54
     metus
    0.53
    Activations Density 0.069%

    No Known Activations