© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 115447
    Prev
    Next
    INDEX
    Explanations

    perhaps, probably, might

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

    This neuron flags Japanese-language sequences (tokens comprising Japanese words or grammar).

    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
    かも知
    -1.20
     violon
    -0.99
     luxem
    -0.95
     唯美
    -0.94
     antena
    -0.93
    かもし
    -0.93
     traverser
    -0.92
     fantasia
    -0.92
     artt
    -0.91
     aile
    -0.91
    POSITIVE LOGITS
     perhaps
    2.28
     probably
    2.16
     might
    1.98
     Perhaps
    1.97
     would
    1.91
    Perhaps
    1.82
     should
    1.79
     likely
    1.75
     surely
    1.71
     maybe
    1.70
    Activations Density 0.001%

    No Known Activations