© 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. 19099
    Prev
    Next
    INDEX
    Explanations

    Hero Dream ID verification

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

    Chinese apps and tech terms

    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
    銠
    0.96
    堊
    0.95
    睪
    0.91
    鰓
    0.88
    啮
    0.86
     анато
    0.81
    蟶
    0.79
    瘧
    0.79
    鳟
    0.79
    鉭
    0.79
    POSITIVE LOGITS
    weixin
    0.88
    baidu
    0.82
     kua
    0.80
     xia
    0.79
     zh
    0.78
    jie
    0.78
     QQ
    0.78
    xiang
    0.78
    qian
    0.78
     shop
    0.76
    Activations Density 0.004%

    No Known Activations