© 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-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 14010
    Prev
    Next
    INDEX
    Explanations

    This neuron detects tokens in non-Latin scripts (e.g. Persian/Arabic text).

    oai_token-act-pair · o4-mini
    Triggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    乱
    0.50
     Pember
    0.50
    絟
    0.49
    端
    0.48
    ในการ
    0.47
    調
    0.46
     ढंग
    0.46
    含
    0.46
    resolver
    0.45
    祭
    0.45
    POSITIVE LOGITS
    lets
    0.64
    Lets
    0.61
    ENSATION
    0.56
    Exceptions
    0.56
    കാന്‍
    0.55
    ቶችን
    0.55
    સાય
    0.55
    IANS
    0.54
    ländischen
    0.54
     Somit
    0.53
    Activations Density 0.007%

    No Known Activations