© 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
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 84093
    Prev
    Next
    INDEX
    Explanations

    code, brackets, desires, religious, food

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ارتی
    0.54
    셔
    0.49
    鈮
    0.49
    GEBURTS
    0.49
    fieldContext
    0.47
     내가
    0.46
    enseignement
    0.46
    AMBI
    0.46
    습
    0.46
    EXTENSION
    0.45
    POSITIVE LOGITS
    www
    0.45
     Bowman
    0.45
     Beverly
    0.44
    w
    0.44
    st
    0.43
    s
    0.43
     Wang
    0.42
     www
    0.42
    讓人
    0.42
    。
    0.42
    Activations Density 0.002%

    No Known Activations