© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 40-GEMMASCOPE-2-RES-16K
    7. 11332
    Prev
    Next
    INDEX
    Explanations

    circumstance or condition

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

    programming contexts and documentation

    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_40_width_16k_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
     цели
    0.47
    нена
    0.42
    વતી
    0.40
    Weather
    0.39
     терито
    0.39
    在這個
    0.38
    本格
    0.38
    ในช่วง
    0.37
     Ventura
    0.37
    ใน
    0.37
    POSITIVE LOGITS
     وفي
    0.67
    看来
    0.59
    ၌
    0.58
    的情况下
    0.57
     případě
    0.54
    においても
    0.52
    ങ്ങളിലും
    0.52
    的基础上
    0.51
    ďaka
    0.51
     denote
    0.49
    Activations Density 0.213%

    No Known Activations