© 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. 144739
    Prev
    Next
    INDEX
    Explanations

    assist and responsibility

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

    responsibility, financial terms, and specific topics

    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
    s
    0.59
    x
    0.58
     GetAll
    0.54
     Nun
    0.54
    sz
    0.51
    নৈতিক
    0.48
    m
    0.48
    鎊
    0.48
    σότε
    0.47
    ירת
    0.47
    POSITIVE LOGITS
     superficial
    0.45
     پت
    0.44
     책임
    0.44
     sequins
    0.44
    ストラップ
    0.44
     பிர
    0.44
     தனி
    0.44
     flimsy
    0.43
     प्राधिकरण
    0.43
     জিজ্ঞাসাবাদ
    0.43
    Activations Density 0.001%

    No Known Activations