© 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. 10279
    Prev
    Next
    INDEX
    Explanations

    technical terms and acronyms

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

    The neuron strongly activates on tokens that are part of proper names or titles (e.g. names of shows, museums, movies, and branded events).

    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
     comes
    0.30
    '
    0.29
     terroir
    0.29
     fared
    0.29
     paltry
    0.29
     gigantic
    0.28
     proves
    0.28
     loses
    0.28
     beginnt
    0.28
     reinvigor
    0.28
    POSITIVE LOGITS
    ﺎ
    0.26
    ỹ
    0.26
     которые
    0.25
    ﻤ
    0.25
     Они
    0.25
    <unused0>
    0.24
     Ото
    0.24
    ↵
    0.23
    <unused443>
    0.23
    <unused1741>
    0.23
    Activations Density 0.000%

    No Known Activations