© 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. 31-GEMMASCOPE-2-RES-16K
    7. 223
    Prev
    Next
    INDEX
    Explanations

    states of readiness or being

    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_16k_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
     如果
    0.21
     或
    0.21
     分
    0.19
    或者
    0.19
     which
    0.18
     空
    0.18
     删除
    0.18
     注
    0.18
     若
    0.18
    或其他
    0.17
    POSITIVE LOGITS
     able
    0.24
     thrilled
    0.22
     addicted
    0.22
     aware
    0.22
     intrigued
    0.21
     humbled
    0.21
     horrified
    0.21
     uitgenodigd
    0.20
     willing
    0.20
     saddened
    0.20
    Activations Density 1.657%

    No Known Activations