© 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-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 31568
    Prev
    Next
    INDEX
    Explanations

    HTML declaration or code block start

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    卧槽
    -1.46
    喏
    -1.45
    咳咳
    -1.44
    多谢
    -1.05
    甭
    -0.98
    是啊
    -0.92
    嚯
    -0.90
    哎呀
    -0.89
    是吗
    -0.86
    谢谢你
    -0.85
    POSITIVE LOGITS
     tsk
    1.67
     hey
    1.65
     hehe
    1.47
    tsk
    1.45
     alas
    1.42
    Tut
    1.38
     tut
    1.37
     haha
    1.34
    Hehe
    1.32
     Hey
    1.30
    Activations Density 0.003%

    No Known Activations