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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 4234
    Prev
    Next
    INDEX
    Explanations

    The main thing this neuron does is detect Hebrew script (Hebrew letters and diacritics).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_24_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    看到
    0.51
    树
    0.49
    只有
    0.48
    情况下
    0.46
    explorer
    0.43
    သင်
    0.42
    便宜
    0.42
    眼睛
    0.42
    以为
    0.41
    做到
    0.41
    POSITIVE LOGITS
     הכ
    1.09
     הת
    0.99
     של
    0.96
     לי
    0.95
     מר
    0.91
     ה
    0.91
     הפ
    0.91
     שלנו
    0.90
     אשר
    0.90
     הר
    0.89
    Activations Density 0.002%

    No Known Activations