© 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. 3790
    Prev
    Next
    INDEX
    Explanations

    economic status, offers, society

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

    line din, later ally, back on

    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
     hätte
    0.23
    ্বরূপ
    0.21
     hätten
    0.21
    trashItem
    0.21
    这也
    0.21
    鸫
    0.21
    Begriffsklär
    0.20
    multiSelectList
    0.20
    xcuser
    0.20
     বেশ
    0.20
    POSITIVE LOGITS
    &
    0.29
    、
    0.25
    리의
    0.25
    ・
    0.24
     및
    0.23
    4
    0.22
     &
    0.21
    ＆
    0.21
    ING
    0.21
    식
    0.21
    Activations Density 6.854%

    No Known Activations