© 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. 7816
    Prev
    Next
    INDEX
    Explanations

    introduction topics

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

    The neuron strongly activates on “introduce” and its morphological variants (e.g. “introduces,” “introducing,” “introduction”), i.e. words signaling presentation of content.

    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
    ర్
    1.34
    ات
    1.18
    ರ್
    1.15
    ра
    1.12
     tror
    1.10
    들의
    1.02
    로
    1.02
    l
    1.01
    స్
    0.99
    клика
    0.99
    POSITIVE LOGITS
     reintroduced
    1.07
     introduction
    1.05
     concepts
    1.02
     introductions
    1.01
     tenets
    1.00
     Introducing
    0.95
     EVs
    0.90
     introduces
    0.89
     但
    0.89
     intro
    0.89
    Activations Density 0.020%

    No Known Activations