© 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. 2024
    Prev
    Next
    INDEX
    Explanations

    joking expressions

    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
    鲔
    0.46
     специфи
    0.43
    缡
    0.42
    髋
    0.41
    堊
    0.41
    柽
    0.40
    甾
    0.40
    黉
    0.40
    缐
    0.40
    硏
    0.38
    POSITIVE LOGITS
     hehe
    0.49
     nodded
    0.46
    ——
    0.46
     scolded
    0.45
     despicable
    0.44
     blushed
    0.44
     domine
    0.43
     hahaha
    0.43
     Xia
    0.43
     murderous
    0.42
    Activations Density 0.005%

    No Known Activations