© 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. 219429
    Prev
    Next
    INDEX
    Explanations

    babies and young children

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

    future of work

    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
    غ
    0.49
    Су
    0.45
    每个
    0.45
     Ajax
    0.45
    داول
    0.45
    它
    0.45
    皰
    0.45
    摘要
    0.44
    دا
    0.43
    قا
    0.43
    POSITIVE LOGITS
    ктери
    0.57
     สร้าง
    0.56
     เด็ก
    0.56
     เร
    0.55
     стиле
    0.54
     дети
    0.53
     子供
    0.53
    TakeVideo
    0.52
     联系
    0.52
     bambini
    0.51
    Activations Density 0.001%

    No Known Activations