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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-16K
    7. 9275
    Prev
    Next
    INDEX
    Explanations

    self- prefix

    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_16k_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
    使用
    0.52
    蛯
    0.51
    叶
    0.50
    煂
    0.50
    氏
    0.49
    При
    0.48
    手
    0.48
    버
    0.48
    ברים
    0.48
    С
    0.48
    POSITIVE LOGITS
     self
    1.71
     Self
    1.54
    self
    1.45
    Self
    1.38
     SELF
    1.25
     सेल्फ
    1.17
     själv
    1.05
     Selbst
    1.02
     само
    0.98
    SELF
    0.98
    Activations Density 0.111%

    No Known Activations