© 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-TRANSCODER-262K
    7. 36806
    Prev
    Next
    INDEX
    Explanations

    Tamil Nadu

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_31_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     Malta
    0.34
     pubs
    0.34
     cafés
    0.34
     caf
    0.34
    Ethiop
    0.33
     اظ
    0.33
     criticality
    0.33
    賭
    0.33
     uns
    0.32
     heap
    0.32
    POSITIVE LOGITS
     Tamil
    0.58
    Tamil
    0.57
     tamil
    0.51
     तमिल
    0.50
    tamil
    0.50
     Nadu
    0.50
     तमिलनाडु
    0.46
     తమిళ
    0.44
    தமிழ்
    0.40
     তাম
    0.40
    Activations Density 0.014%

    No Known Activations