© 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. 122662
    Prev
    Next
    INDEX
    Explanations

    page numbers and abbreviations

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

    page numbers and article references

    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
    丿
    0.38
    ","
    0.37
    来自于
    0.37
    级别的
    0.36
    cordova
    0.36
    となりました
    0.36
    த்தினை
    0.36
    /*!
    0.36
     автомобі
    0.36
    带有
    0.36
    POSITIVE LOGITS
     page
    0.75
     pp
    0.70
     pages
    0.69
    page
    0.64
    頁
    0.62
     ibid
    0.61
     pg
    0.59
     पेज
    0.58
    第
    0.57
     페이지
    0.57
    Activations Density 0.099%

    No Known Activations