© 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. 44023
    Prev
    Next
    INDEX
    Explanations

    Japanese culture, martial arts, ninjas

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

    This neuron activates on Japanese cultural terms and loanwords (e.g. samurai, bonsai, sumo, ronin, dojo).

    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
    螓
    -3.00
    इटम
    -2.42
    sudadera
    -2.31
    Ꭽ
    -2.31
    t
    -2.28
    他们的
    -2.25
    pulseira
    -2.25
    d
    -2.23
    n
    -2.19
    ⟝
    -2.19
    POSITIVE LOGITS
    邂
    2.33
    ные
    2.17
    𖣘
    2.16
    All
    2.13
    ных
    2.11
    ный
    2.08
    色々な
    2.08
     IBRARY
    2.05
    ・・・・・
    2.02
     右
    1.98
    Activations Density 0.008%

    No Known Activations