© 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
    2. Gemma-3-12B
    3. 24-GEMMASCOPE-2-RES-16K
    4. 11699
    Prev
    Next
    INDEX
    Explanations

    recent scientific

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

    The neuron reliably lights up on section‐heading or topic label tokens—that is, words that introduce a new section or heading in the document.

    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_24_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
     Masa
    0.85
     lomba
    0.77
    '
    0.77
     cibo
    0.76
     entre
    0.75
     Adresse
    0.75
     nourriture
    0.75
     ù
    0.75
     després
    0.75
     fermeture
    0.74
    POSITIVE LOGITS
    ным
    1.01
    туры
    0.88
    ной
    0.88
    IRED
    0.80
    зной
    0.79
    ная
    0.78
     herringbone
    0.78
    бе
    0.77
    峩
    0.77
    无疑
    0.77
    Activations Density 0.000%

    No Known Activations