© 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
    5. 53-GEMMASCOPE-2-RES-65K
    7. 3106
    Prev
    Next
    INDEX
    Explanations

    i following core

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

    programming index variable i

    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
    ╁
    0.39
    ථ
    0.39
     حکم
    0.38
    ヴ
    0.38
    𒉺
    0.38
    মানে
    0.37
    rš
    0.37
     करूंगा
    0.36
    ຫາ
    0.35
    ម្ត
    0.35
    POSITIVE LOGITS
     i
    3.88
    i
    2.34
    ｉ
    2.05
    𝑖
    2.03
     ii
    1.76
    𝐢
    1.56
    𝒊
    1.56
    𝗶
    1.50
    ⅰ
    1.50
    ᵢ
    1.47
    Activations Density 0.135%

    No Known Activations