© 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. 10-GEMMASCOPE-RES-131K
    7. 10045
    Prev
    Next
    INDEX
    Explanations

    learning, mathematics, and study

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

    The neuron activates on the Japanese morpheme “gaku” (including the kanji 学/學) whenever it appears inside words or names.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    
    -2.78
    他才
    -2.63
    逦
    -2.59
     raiſ
    -2.56
    嗵
    -2.45
    ⽌
    -2.39
     biologie
    -2.39
    éroport
    -2.36
    籴
    -2.34
    ネイル
    -2.27
    POSITIVE LOGITS
    {
    4.63
    3
    2.66
    4
    2.64
    8
    2.64
    g
    2.63
    5
    2.59
    aliśmy
    2.58
    )
    2.55
    
    2.53
    謦
    2.53
    Activations Density 0.001%

    No Known Activations