© 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-65K
    7. 6132
    Prev
    Next
    INDEX
    Explanations

    tradition, Confucianism, Taoism, Buddhism

    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
    演唱
    0.39
    वेळी
    0.37
    िरिक्स
    0.37
     inlet
    0.37
    最大的
    0.36
     همیشه
    0.36
     routine
    0.36
    字
    0.35
    arette
    0.35
    ₁(
    0.34
    POSITIVE LOGITS
     astronaut
    0.42
    astronaut
    0.40
    បែប
    0.38
     تاکہ
    0.38
     kabel
    0.38
     anatom
    0.38
     tapping
    0.38
     शास्त्रों
    0.37
     jogador
    0.36
    lon
    0.36
    Activations Density 0.027%

    No Known Activations