© 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
    5. 53-GEMMASCOPE-2-RES-65K
    7. 7415
    Prev
    Next
    INDEX
    Explanations

    URLs and file paths

    np_acts-logits-general · gemini-2.5-flash-lite

    URLs and domains

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_53_width_65k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     sexuales
    0.26
     minifyEnabled
    0.25
     bxc
    0.25
     冖
    0.24
     photospheres
    0.23
     kttt
    0.23
     📫
    0.23
     Михаил
    0.23
     ديسمبر
    0.22
    ྞ
    0.22
    POSITIVE LOGITS
    C
    0.23
    El
    0.23
    Okay
    0.22
    Blank
    0.22
    一块
    0.21
    THE
    0.21
    In
    0.20
    CH
    0.20
    Case
    0.20
    //
    0.20
    Activations Density 0.012%

    No Known Activations