© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 322
    Prev
    Next
    INDEX
    Explanations

    having a fever

    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_16k_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
    婀
    0.19
    朝鲜
    0.19
    ították
    0.18
     Polaroid
    0.18
    ettiin
    0.18
     നാല
    0.18
     Congressman
    0.17
    akkhan
    0.17
     ત્રણ
    0.17
     Salford
    0.17
    POSITIVE LOGITS
     products
    0.18
     dlatego
    0.18
     শব্দটি
    0.17
    饌
    0.16
     styles
    0.16
    體驗
    0.16
    WORK
    0.16
    centric
    0.16
     medications
    0.16
     lainnya
    0.16
    Activations Density 3.681%

    No Known Activations