© 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-262K
    7. 21023
    Prev
    Next
    INDEX
    Explanations

    sentences starting with 'my' or 'i'

    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_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
     बातम्या
    0.57
     namani
    0.55
     hoera
    0.55
     فرنسا
    0.55
    ปัญหา
    0.54
     rupani
    0.54
    ه‌ها
    0.52
    ၊
    0.52
    िशनर
    0.52
     визна
    0.52
    POSITIVE LOGITS
    am
    0.77
     the
    0.62
     or
    0.61
     of
    0.59
    A
    0.59
    d
    0.57
     has
    0.56
    기
    0.55
     from
    0.54
     de
    0.54
    Activations Density 0.176%

    No Known Activations