© 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. 34-GEMMASCOPE-RES-131K
    7. 108274
    Prev
    Next
    INDEX
    Explanations

    japanese phrases and english technical terms

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

    This neuron tends to spike on relatively long or uncommon words (including multi‐character Japanese compounds and infrequent English 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
    踔
    -1.00
    我自己
    -0.97
     cucharada
    -0.93
     yourselves
    -0.92
    före
    -0.92
     sometimes
    -0.90
    先生が
    -0.88
    Each
    -0.87
     علاوه
    -0.86
     иногда
    -0.85
    POSITIVE LOGITS
    optarg
    1.10
    再次
    1.09
    ｆ
    1.06
     используя
    1.03
     erneut
    1.02
    Ｚ
    1.02
    菈
    1.02
    bParam
    1.02
     aufgrund
    1.01
    ochim
    1.01
    Activations Density 0.001%

    No Known Activations