© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 6853
    Prev
    Next
    INDEX
    Explanations

    anime and Japanese pop culture

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

    This neuron detects Japanese anime (or similar) titles written in the form “X no Y.”

    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
     recibirá
    -0.80
    tenor
    -0.77
     receber
    -0.75
    ícone
    -0.75
     verlieren
    -0.74
     présentée
    -0.74
     presentaron
    -0.73
     aplican
    -0.73
     escolher
    -0.73
     começou
    -0.73
    POSITIVE LOGITS
    Soul
    1.01
     Soul
    0.93
     mies
    0.87
     maka
    0.84
     soul
    0.84
     Wavelength
    0.79
    Evans
    0.78
     Meisters
    0.77
     scythe
    0.77
    Organization
    0.76
    Activations Density 0.006%

    No Known Activations