© 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. 25736
    Prev
    Next
    INDEX
    Explanations

    Q: questions with technical queries

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

    The neuron strongly activates on formatted anime/manga series titles (e.g., “Ao no Exorcist:” or “My Hero Academia – Episode 18”).

    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
    itola
    -0.77
     Thug
    -0.77
     Projekte
    -0.75
     ผ้า
    -0.74
    ronyms
    -0.73
    ⠄
    -0.73
     Stout
    -0.73
    Jared
    -0.72
    лети
    -0.71
    ە
    -0.71
    POSITIVE LOGITS
     flaming
    0.84
     Everest
    0.81
     Michaelis
    0.79
     Gehen
    0.76
    称号
    0.73
    ferd
    0.71
    下手
    0.70
    痙
    0.69
    ridor
    0.68
    资格
    0.67
    Activations Density 0.015%

    No Known Activations