Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-65K
    4. 56589
    Prev
    Next
    INDEX
    Explanations

    images and lake

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_65k_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
    Какой
    0.53
    أ
    0.50
    ه
    0.48
    Die
    0.47
    ল
    0.46
    دا
    0.45
    جه
    0.45
    Ди
    0.45
    ா
    0.45
    Navy
    0.44
    POSITIVE LOGITS
     (
    0.47
    ene
    0.46
     ކުރ
    0.45
     populate
    0.45
     testa
    0.45
     dragging
    0.44
     president
    0.44
    牷
    0.44
     tester
    0.44
     resten
    0.44
    Activations Density 0.001%

    No Known Activations