© 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-IT
    5. 16-GEMMASCOPE-2-RES-65K
    7. 542
    Prev
    Next
    INDEX
    Explanations

    code and non-english word endings

    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_16_width_65k_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
    ون
    0.49
    ма
    0.44
    In
    0.40
    M
    0.39
    نا
    0.38
    ים
    0.38
    х
    0.38
    User
    0.38
    на
    0.37
    Z
    0.37
    POSITIVE LOGITS
    ется
    0.39
    是
    0.37
    は
    0.35
    은
    0.34
    습니다
    0.34
    ا۔
    0.33
    )])
    0.32
    ا
    0.31
    াতের
    0.30
    ۔
    0.30
    Activations Density 1.352%

    No Known Activations