© 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. 100941
    Prev
    Next
    INDEX
    Explanations

    words and phrases

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

    definitions and comparisons

    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
     cible
    0.45
    ulse
    0.45
    กล้
    0.39
    ච්
    0.39
     Tomcat
    0.38
    줘
    0.38
    icycle
    0.37
     بیگ
    0.37
     clor
    0.37
    রূপে
    0.37
    POSITIVE LOGITS
     考え
    0.48
    播
    0.47
     និង
    0.47
    দ্ধ
    0.47
    ㄦ
    0.47
     遊ん
    0.46
    鈐
    0.46
     आणि
    0.46
     تشتغل
    0.46
    沍
    0.46
    Activations Density 0.001%

    No Known Activations