© 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. 33618
    Prev
    Next
    INDEX
    Explanations

    bibliographical references

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

    structured text and code keywords

    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
    東京
    0.55
    i
    0.54
    届け
    0.51
    LAYOUT
    0.50
    ラ
    0.47
    姫
    0.47
    मैं
    0.47
    続ける
    0.47
    ホテル
    0.47
    ミ
    0.46
    POSITIVE LOGITS
    िरिक्स
    0.53
     Конститу
    0.53
     ৃ
    0.52
     социально
    0.51
     คณิตศาสตร์
    0.50
     ثلاث
    0.48
     уравнения
    0.46
    నులు
    0.46
     απ
    0.45
     =-
    0.45
    Activations Density 0.001%

    No Known Activations