© 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. 40-GEMMASCOPE-2-RES-65K
    7. 911
    Prev
    Next
    INDEX
    Explanations

    when Chong

    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_40_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
    但是我
    0.30
    /
    0.29
     我们
    0.29
     break
    0.28
     মানুষদের
    0.28
    \
    0.27
    如果我们
    0.26
     soll
    0.26
     Should
    0.26
     There
    0.25
    POSITIVE LOGITS
     они
    0.36
    佢
    0.35
     તેઓ
    0.33
    they
    0.32
     they
    0.32
     তারা
    0.31
    它
    0.31
    薨
    0.31
     вони
    0.30
     она
    0.29
    Activations Density 0.585%

    No Known Activations