© 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-IT
    5. 12-GEMMASCOPE-2-RES-16K
    7. 4295
    Prev
    Next
    INDEX
    Explanations

    Final Answer

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_12_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ダー
    1.09
     radish
    1.09
    ◦
    1.05
     nymphs
    1.02
    খ
    1.02
    鍒
    1.02
     dutiful
    0.98
    鈞
    0.97
    мо
    0.96
    нили
    0.96
    POSITIVE LOGITS
     концов
    1.41
    ੀ
    1.18
    を迎
    1.10
    結論
    1.09
     koń
    1.08
     المط
    1.05
    gült
    1.05
    បញ្ចប់
    1.05
     итоге
    1.04
    orsement
    1.03
    Activations Density 0.759%

    No Known Activations