© 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. 367
    Prev
    Next
    INDEX
    Explanations

    user prompts

    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
    न
    1.25
    нің
    1.03
     intestin
    1.02
    𝕒
    1.00
    ě
    1.00
    𝒆
    1.00
    ále
    0.98
    􀂃
    0.97
    ра
    0.96
    으로
    0.96
    POSITIVE LOGITS
    ت
    0.98
    ب
    0.97
    ال
    0.96
    hai
    0.88
    yang
    0.88
    י
    0.86
    श्वर
    0.83
    יים
    0.82
    hubungan
    0.78
    ../
    0.78
    Activations Density 0.001%

    No Known Activations