© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 38658
    Prev
    Next
    INDEX
    Explanations

    Japanese/Chinese names and terms

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

    The neuron activates on non‐Latin (CJK) characters, i.e. tokens written in Chinese or Japanese script.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     αγ
    -1.08
     jardim
    -1.05
     a
    -1.04
     our
    -1.00
    .”
    -0.99
     camiset
    -0.96
     teus
    -0.95
    𝕘
    -0.91
     mestre
    -0.91
     bơi
    -0.90
    POSITIVE LOGITS
    ışık
    1.23
     aislada
    1.19
     dibujar
    1.09
     cuadrada
    1.09
    ARROLL
    1.07
    sprit
    1.05
    gün
    1.02
     associée
    1.02
     admiten
    1.02
    iX
    1.02
    Activations Density 0.019%

    No Known Activations