© 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-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 3139
    Prev
    Next
    INDEX
    Explanations

    various languages

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

    The neuron strongly activates on sequences of Arabic‐script characters (Arabic words).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ベツ
    -0.84
    Sew
    -0.81
    жалуйста
    -0.77
     schreib
    -0.76
     Ra
    -0.76
    igera
    -0.75
     étan
    -0.75
    łat
    -0.74
     opposed
    -0.72
    แล้ว
    -0.72
    POSITIVE LOGITS
     soru
    0.88
     करेंगे
    0.83
     thích
    0.82
     usato
    0.78
    なので
    0.78
    rennen
    0.77
    råd
    0.75
     tiga
    0.75
    一の
    0.75
     naik
    0.73
    Activations Density 0.005%

    No Known Activations