© 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. 24-GEMMASCOPE-2-RES-16K
    7. 395
    Prev
    Next
    INDEX
    Explanations

    The neuron flags rare proper-noun tokens—that is, unusual capitalized names of people, places, or organizations.

    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
     proceder
    0.28
     phẳng
    0.28
    ركات
    0.27
     каран
    0.27
     ingresso
    0.27
     ecmaVersion
    0.27
     />);
    0.27
     positi
    0.26
    rictional
    0.26
     pertinente
    0.26
    POSITIVE LOGITS
     south
    0.35
    をはじめ
    0.35
    我现在
    0.35
    ian
    0.34
    我们在
    0.33
    adı
    0.32
     north
    0.32
     west
    0.32
     portugu
    0.32
    V
    0.32
    Activations Density 0.000%

    No Known Activations