© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 11672
    Prev
    Next
    INDEX
    Explanations

    conditional logic and code structure

    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_262k_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
     คว
    0.27
     ри
    0.27
    א
    0.26
     кор
    0.26
    𝖺
    0.26
     боле
    0.26
     corrosive
    0.25
    क़
    0.25
     synapses
    0.25
     diarrhoea
    0.25
    POSITIVE LOGITS
    if
    0.39
    Якщо
    0.28
    പ്പെടുന്ന
    0.27
    while
    0.27
    ኙ
    0.26
    ując
    0.26
    wijl
    0.26
     যদি
    0.25
    avlja
    0.24
    ándose
    0.24
    Activations Density 0.206%

    No Known Activations