© 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. 7497
    Prev
    Next
    INDEX
    Explanations

    urls

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

    This neuron lights up on short, title-style or label-style capitalized phrases (e.g. headings, section names, or standalone names).

    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
     (
    0.57
     Negra
    0.56
     ofthe
    0.55
     They
    0.55
     (#
    0.54
     meja
    0.52
     striated
    0.52
     Once
    0.52
     เขา
    0.52
    ,
    0.52
    POSITIVE LOGITS
    Ма
    0.62
    ኣ
    0.60
    Ле
    0.57
    Па
    0.57
    マ
    0.56
    COMMON
    0.55
    MAN
    0.54
    Quran
    0.53
    ман
    0.52
    gradle
    0.52
    Activations Density 0.003%

    No Known Activations