© 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. 10-GEMMASCOPE-RES-131K
    7. 72955
    Prev
    Next
    INDEX
    Explanations

    Richard Cordray, Skip Hire

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

    The neuron activates on adjectives (tokens tagged with “_JJ”).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    Интере
    -1.95
    鬭
    -1.83
    梦见
    -1.83
    Клю
    -1.80
     unrelenting
    -1.80
     Tienen
    -1.78
    -¡
    -1.78
     sociala
    -1.77
     brosse
    -1.76
    *</
    -1.75
    POSITIVE LOGITS
     decidedly
    2.22
    蹰
    2.09
    都想
    2.05
     was
    1.97
    >
    1.91
     "'
    1.89
    during
    1.87
     significantly
    1.86
     called
    1.86
     exceedingly
    1.84
    Activations Density 0.001%

    No Known Activations