© 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. 7892
    Prev
    Next
    INDEX
    Explanations

    hole

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

    hole and holes

    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
     DOCUMENTS
    0.41
     sectarian
    0.40
    সপ
    0.39
    葳
    0.39
     secteur
    0.38
    riezmann
    0.38
     سع
    0.38
    писки
    0.37
    ㄻ
    0.37
    sectors
    0.37
    POSITIVE LOGITS
     hole
    4.50
     holes
    4.47
     Holes
    4.06
     Hole
    4.03
    hole
    3.92
    holes
    3.84
    穴
    3.50
     отверсти
    3.28
     lỗ
    2.66
     छेद
    2.58
    Activations Density 0.148%

    No Known Activations