© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 15432
    Prev
    Next
    INDEX
    Explanations

    existing businesses

    np_acts-logits-general · gemini-2.5-flash-lite

    existing maintenance

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_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
    ౌ
    0.39
    zinha
    0.38
    ે
    0.38
    ͌
    0.38
    ൂര
    0.37
     tia
    0.36
    ohia
    0.36
     grasa
    0.36
     hinn
    0.36
    坤
    0.36
    POSITIVE LOGITS
     existing
    0.70
    Existing
    0.69
    既存
    0.69
     Existing
    0.68
    existing
    0.66
     EXISTING
    0.61
    Deletion
    0.57
     существу
    0.56
     বিদ্যমান
    0.55
    现有
    0.55
    Activations Density 0.358%

    No Known Activations