© 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-3-12B
    5. 41-GEMMASCOPE-2-RES-65K
    7. 13825
    Prev
    Next
    INDEX
    Explanations

    fang

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_41_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
    ₄
    0.80
    <sup>
    0.77
     ${
    0.74
    ₆
    0.73
    ₃
    0.71
    ₁
    0.70
     ²
    0.70
    ${
    0.68
    ⁴
    0.66
     ¹
    0.65
    POSITIVE LOGITS
     방
    1.69
    방
    1.61
    fang
    1.15
     fang
    1.15
    方
    1.13
    Fang
    1.07
     phương
    1.05
     Fang
    1.04
    防
    1.03
    方的
    1.02
    Activations Density 0.004%

    No Known Activations