© 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. 7012
    Prev
    Next
    INDEX
    Explanations

    element needs

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

    It responds to tokens associated with numbered or list‐style formatting (e.g. section headings, numeric indicators, and the parentheses/colons around list numbers).

    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
    ദം
    0.73
    ate
    0.73
    страницу
    0.73
    ட்டிக்க
    0.71
     ప్ర
    0.71
    ahr
    0.70
    ApiPath
    0.70
    arb
    0.68
    evo
    0.67
     прошлого
    0.67
    POSITIVE LOGITS
     있습니다
    0.79
    ◢
    0.79
    쿵
    0.79
     terdapat
    0.78
    합니다
    0.77
    在一个
    0.76
     USART
    0.75
     sucre
    0.74
     IMPORTANT
    0.74
    떤
    0.74
    Activations Density 0.001%

    No Known Activations