© 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. 30893
    Prev
    Next
    INDEX
    Explanations

    ask questions, request actions

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

    This neuron activates on romanized Hindi 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
    แน
    -0.81
    咧
    -0.77
    yes
    -0.69
    ≐
    -0.67
     opravdu
    -0.67
    做好
    -0.66
    ᐃ
    -0.65
    なんだろう
    -0.65
     politika
    -0.65
    ourcing
    -0.64
    POSITIVE LOGITS
    啊
    2.53
    สิ
    1.94
    呀
    1.91
    ไง
    1.58
    嘛
    1.53
    ではない
    1.48
     啊
    1.46
     دیگه
    1.33
    นี่
    1.32
    不是
    1.28
    Activations Density 0.036%

    No Known Activations