© 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. 31-GEMMASCOPE-2-RES-16K
    7. 6221
    Prev
    Next
    INDEX
    Explanations

    saving time or resources

    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_31_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
    nobyl
    0.64
    不安定
    0.62
     Sandbox
    0.57
     নেতৃত্ব
    0.55
     Ensuring
    0.55
     Slowly
    0.55
     ENS
    0.53
    쨍
    0.52
    україн
    0.52
    StdHandle
    0.52
    POSITIVE LOGITS
    节省
    2.06
     rispar
    1.92
     saves
    1.90
     ahorrar
    1.82
     ahorro
    1.79
     saving
    1.77
     savings
    1.74
    ไม่ต้อง
    1.68
     Saves
    1.66
    saves
    1.66
    Activations Density 1.056%

    No Known Activations