© 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. 158765
    Prev
    Next
    INDEX
    Explanations

    responsible for, large cap, overseas transactions

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

    money, own, AI, very, calculating

    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
    傗
    0.56
    ically
    0.47
    ii
    0.45
    当然
    0.45
    örungen
    0.44
    insel
    0.44
     всички
    0.43
    if
    0.42
     dient
    0.42
    i
    0.42
    POSITIVE LOGITS
    𝚁
    0.50
     ਲੈ
    0.44
     despacho
    0.43
    寫
    0.42
     반려동
    0.41
     مكتب
    0.41
    CES
    0.41
    IDEA
    0.39
    DTD
    0.39
    ONS
    0.39
    Activations Density 0.000%

    No Known Activations