© 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. 22-GEMMASCOPE-RES-131K
    7. 28084
    Prev
    Next
    INDEX
    Explanations

    Saint-Michel, James Bond

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

    The neuron activates strongly on capitalized tokens that are part of proper names (e.g. people, products, species, titles).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     their
    -1.02
    궁
    -0.93
     botines
    -0.92
    以来
    -0.90
    ambut
    -0.90
     jejich
    -0.89
    jej
    -0.89
    biskan
    -0.88
     kré
    -0.87
    гиоз
    -0.87
    POSITIVE LOGITS
     himmel
    0.93
    ][-
    0.85
     who
    0.83
     січня
    0.81
     către
    0.81
    仅仅
    0.81
    两次
    0.80
    훗
    0.79
    仅
    0.79
     возрасте
    0.77
    Activations Density 0.027%

    No Known Activations