© 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. 74
    Prev
    Next
    INDEX
    Explanations

    `Hopefully`, `maybe`, `definitely`, `perhaps`

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

    the hedging phrase “I guess.”

    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
    ，
    0.69
    ли
    0.68
    ்
    0.64
    ла
    0.63
    ,”
    0.62
    ,
    0.61
    ،
    0.61
    ları
    0.59
    ó
    0.59
    li
    0.58
    POSITIVE LOGITS
     बाकी
    0.84
    expec
    0.83
    aurait
    0.79
     nacionais
    0.78
    sons
    0.77
     coloquei
    0.77
     Мы
    0.75
    permit
    0.75
     Lembrando
    0.74
    buscar
    0.73
    Activations Density 0.002%

    No Known Activations