© 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. 7045
    Prev
    Next
    INDEX
    Explanations

    real thing

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

    The neuron strongly activates on the word “real” (as in “the real deal,” “real thing,” etc.), i.e. uses of “real” to signal authenticity.

    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
     组
    -0.80
    方がいい
    -0.78
    感觉到
    -0.76
    anges
    -0.75
     durumu
    -0.74
     constaté
    -0.74
     卡片
    -0.73
     direito
    -0.73
     tulips
    -0.71
    燜
    -0.71
    POSITIVE LOGITS
     thing
    3.39
    thing
    1.99
     Thing
    1.98
     THING
    1.84
    Thing
    1.84
     вещь
    1.48
     cosa
    1.38
     coisa
    1.32
    THING
    1.32
     דבר
    1.07
    Activations Density 0.024%

    No Known Activations