© 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. 129190
    Prev
    Next
    INDEX
    Explanations

    determiner followed by verb or noun

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

    keywords for 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
    従業
    0.48
    少年
    0.47
    เมื่อ
    0.47
    见
    0.47
    眈
    0.47
    愛
    0.46
    াঙ্গীর
    0.46
    爱
    0.46
    ético
    0.46
    婀
    0.45
    POSITIVE LOGITS
     mensaje
    0.46
     principi
    0.46
     distinct
    0.43
     osim
    0.43
     demarc
    0.42
     dermat
    0.41
     circum
    0.41
     confl
    0.41
     mend
    0.40
     legislative
    0.40
    Activations Density 0.013%

    No Known Activations