Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-27B-IT
    3. 16-GEMMASCOPE-2-RES-262K
    4. 5099
    Prev
    Next
    INDEX
    Explanations

    sentence 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_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
     สื
    0.43
    σταν
    0.42
    ![](
    0.41
    gmzy
    0.41
    しくは
    0.41
    ncnc
    0.41
     Buckeyes
    0.41
     Rockville
    0.41
     प्रोत्साहन
    0.40
     TestAvg
    0.40
    POSITIVE LOGITS
     and
    0.66
    ق
    0.61
    ہ
    0.57
     which
    0.55
    ING
    0.52
    ین
    0.51
    f
    0.49
     as
    0.49
    ف
    0.49
    ח
    0.49
    Activations Density 0.000%

    No Known Activations