© 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. 121452
    Prev
    Next
    INDEX
    Explanations

    specific results and reviews

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

    systems and abstract concepts

    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
     churches
    0.52
    -|
    0.48
    ang
    0.48
    in
    0.47
    ed
    0.46
    jc
    0.46
    h
    0.46
     choir
    0.45
     कॉलेजों
    0.44
     slate
    0.44
    POSITIVE LOGITS
     透明
    0.54
     显示
    0.52
     PROVID
    0.51
    iteit
    0.47
     北京
    0.47
     IMPORT
    0.46
    庣
    0.46
    天津
    0.46
     插
    0.46
     ತೆಗೆದುಕೊಳ್ಳ
    0.46
    Activations Density 0.001%

    No Known Activations