© 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. 92382
    Prev
    Next
    INDEX
    Explanations

    arbitrary

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

    The neuron strongly activates on common English function words—especially prepositions (in, of, for) and articles (a, the).

    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
    ylim
    -0.80
     deepcopy
    -0.77
     Alabama
    -0.76
    MainThread
    -0.75
     Too
    -0.74
    женной
    -0.74
     instinctively
    -0.73
    efully
    -0.73
    }^{-
    -0.73
    Ala
    -0.73
    POSITIVE LOGITS
     arbitrary
    5.69
    arbitrary
    4.97
     Arbitrary
    4.19
    Arbit
    4.03
    任意
    4.00
     arbitrarily
    3.58
     belieb
    3.50
     arbit
    3.38
     arbitrar
    3.22
     any
    3.16
    Activations Density 0.271%

    No Known Activations