Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-12B
    3. 12-GEMMASCOPE-2-RES-16K
    4. 181
    Prev
    Next
    INDEX
    Explanations

    academic and foreign terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_12_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
     a
    0.77
    𝐄
    0.76
     তোমার
    0.76
    о
    0.76
     the
    0.73
     with
    0.73
     когда
    0.73
     from
    0.71
     all
    0.71
    จาก
    0.71
    POSITIVE LOGITS
    סים
    0.64
    ::{
    0.62
     gobiernos
    0.59
    ,
    0.59
     transnational
    0.58
    zelfde
    0.58
     razvoja
    0.57
     egyes
    0.57
    .'”
    0.57
     सिलसिले
    0.57
    Activations Density 0.513%

    No Known Activations