© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 176833
    Prev
    Next
    INDEX
    Explanations

    Arabic language content

    np_acts-logits-general · gemini-2.5-flash-lite

    abstract concepts and states

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    buf
    0.46
     pym
    0.43
    <0x9F>
    0.41
     adv
    0.40
     legg
    0.40
     didn
    0.39
    llllll
    0.39
    Int
    0.39
    artigen
    0.39
     acetylene
    0.39
    POSITIVE LOGITS
    كة
    0.52
     اسرائیل
    0.52
    قب
    0.49
     مدیریت
    0.49
     উপকরণ
    0.49
    د
    0.48
     اسرائیلی
    0.48
    ಯ
    0.48
    锷
    0.47
    COTT
    0.47
    Activations Density 0.000%

    No Known Activations