© 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. 12-GEMMASCOPE-2-RES-16K
    7. 270
    Prev
    Next
    INDEX
    Explanations

    internet urls and domain names

    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
    에는
    0.82
    が高い
    0.80
    nson
    0.80
    をしている
    0.79
     Induction
    0.77
     포함
    0.74
     Officially
    0.73
    쯤
    0.73
     aucun
    0.73
    <a>
    0.72
    POSITIVE LOGITS
    ج
    0.97
    ajemen
    0.92
    िन्न
    0.88
    ले
    0.88
    çalves
    0.86
    urés
    0.86
    もしくは
    0.86
    ឡិចត្រូ
    0.85
     ショルダーバッグ
    0.85
    onym
    0.85
    Activations Density 0.000%

    No Known Activations