© 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. 81591
    Prev
    Next
    INDEX
    Explanations

    Pokémon "diamond", "Light", "Gold"

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

    The neuron fires strongly on tokens belonging to Pokémon game titles or version names.

    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
    Cinderella
    -0.82
    ксана
    -0.79
    ürzen
    -0.74
    iexcl
    -0.74
    伟大
    -0.73
     адре
    -0.71
    лой
    -0.70
     Miner
    -0.70
    тою
    -0.69
     MEG
    -0.69
    POSITIVE LOGITS
     Sin
    0.84
     Emotion
    0.82
     Galactic
    0.76
     Сти
    0.75
    uš
    0.74
     Nombre
    0.74
    ską
    0.73
     الإمارات
    0.73
    jsh
    0.73
     rema
    0.72
    Activations Density 0.016%

    No Known Activations