© 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. 1012
    Prev
    Next
    INDEX
    Explanations

    The neuron fires most strongly on key topic nouns—especially proper names and other content words that signal the main subjects or entities in a text.

    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
     mittels
    0.64
    தாவது
    0.64
     такие
    0.62
     jeweils
    0.59
    ப்பட்டன
    0.58
     slike
    0.56
     alrededores
    0.56
     S
    0.56
     такую
    0.55
     tekrar
    0.54
    POSITIVE LOGITS
     deserving
    1.05
     worthy
    1.00
     extraordinaire
    0.90
     для
    0.89
     whose
    0.89
    whose
    0.87
    ที่มี
    0.82
    สำหรับ
    0.82
     capable
    0.82
     possessing
    0.81
    Activations Density 1.064%

    No Known Activations