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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 40854
    Prev
    Next
    INDEX
    Explanations

    发, recommended, values, father

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

    describing requirements or conditions

    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_31_width_262k_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
    T
    0.49
    τι
    0.48
     Indi
    0.46
    icis
    0.44
     Galileo
    0.43
    onu
    0.43
     coarser
    0.42
     Comte
    0.42
    Tl
    0.42
     comprendere
    0.42
    POSITIVE LOGITS
    的发
    0.47
     测试
    0.44
    是有
    0.44
    厂家
    0.43
    训练
    0.43
    门
    0.43
    甙
    0.43
     发
    0.43
     發
    0.43
    的全
    0.42
    Activations Density 0.000%

    No Known Activations