© 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. 115627
    Prev
    Next
    INDEX
    Explanations

    juniors, wants, happening, out

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

    Neural Networks

    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
    COL
    0.49
     mainly
    0.45
    0.45
     macro
    0.44
     vacío
    0.43
     documental
    0.42
     podemos
    0.42
    <0xE3>
    0.42
    ‌ترین
    0.42
     vocal
    0.42
    POSITIVE LOGITS
     skepticism
    0.52
    ផ្គ
    0.51
     ਪ
    0.51
     конкурс
    0.50
    signup
    0.49
    ខ្ញ
    0.49
    ंग
    0.48
     एक्सेस
    0.48
     Кон
    0.48
     திருப்பி
    0.48
    Activations Density 0.000%

    No Known Activations