© 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. 50411
    Prev
    Next
    INDEX
    Explanations

    Kong, empty space, air conditioner

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

    The neuron strongly activates on the proper noun “Kong,” i.e. occurrences of the token “Kong” in text.

    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
    Crow
    -0.77
    priv
    -0.76
     pov
    -0.75
     agendas
    -0.70
    andina
    -0.70
    muş
    -0.70
     Warner
    -0.69
     derde
    -0.69
    Tim
    -0.69
    Made
    -0.69
    POSITIVE LOGITS
    相对
    0.71
     空
    0.70
    空
    0.70
    ILEY
    0.68
     beating
    0.67
     السلط
    0.66
     out
    0.66
    摺
    0.64
    lecture
    0.64
     air
    0.64
    Activations Density 0.024%

    No Known Activations