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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 5551
    Prev
    Next
    INDEX
    Explanations

    foreign language verbs and operations

    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
    _
    0.34
    *,
    0.31
    {
    0.30
    INCLUDING
    0.30
    의
    0.30
    들과
    0.29
     năm
    0.29
    (
    0.29
    도의
    0.29
    やかな
    0.29
    POSITIVE LOGITS
     दट
    0.35
     മികച്ച
    0.34
     risolvere
    0.33
     mejorar
    0.33
    رسٹ
    0.32
     personalizar
    0.32
     Umsetzung
    0.32
     решать
    0.32
     делать
    0.31
     বিরক্ত
    0.31
    Activations Density 0.000%

    No Known Activations