© 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. 16884
    Prev
    Next
    INDEX
    Explanations

    legal, financial, political, exhibition, or online community topics

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

    website exchanges

    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
     그
    0.43
     ל
    0.42
     ਹੈ
    0.39
     הא
    0.38
     nke
    0.38
    کی
    0.37
    ก็
    0.37
     జగ
    0.37
     казіно
    0.37
     جهان
    0.37
    POSITIVE LOGITS
    োয়ার
    0.35
     privind
    0.34
     sculpting
    0.34
     handcrafted
    0.34
     silencing
    0.34
    Assistant
    0.33
    δου
    0.32
    MPs
    0.32
    .
    0.32
    ле
    0.32
    Activations Density 0.271%

    No Known Activations