© 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-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 80773
    Prev
    Next
    INDEX
    Explanations

    foreign language phrases

    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
    Negative Logits
    ри
    0.53
    ς
    0.47
    s
    0.47
     creatividad
    0.46
    бер
    0.45
     libertà
    0.44
    ोप
    0.44
    ク
    0.44
    <0xEC>
    0.43
     protección
    0.43
    POSITIVE LOGITS
    额
    0.46
     ခု
    0.45
    ství
    0.45
     쪽
    0.44
     মানে
    0.44
    otá
    0.44
     vegg
    0.44
    ດ້ານ
    0.43
    ekkür
    0.43
     ഒഴ
    0.43
    Activations Density 0.004%

    No Known Activations