© 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. 2457
    Prev
    Next
    INDEX
    Explanations

    studies focused on either/or

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

    The neuron activates on technical and scientific research terminology—words like physicists, mathematicians, analysis, models, and related discipline‐specific nouns.

    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
     three
    -1.64
     seven
    -1.59
     would
    -1.54
     any
    -1.51
     four
    -1.50
     six
    -1.44
     eight
    -1.43
     five
    -1.41
     when
    -1.34
     two
    -1.34
    POSITIVE LOGITS
    either
    2.34
     either
    2.17
    Either
    2.09
    mostly
    1.79
     Either
    1.73
    Mostly
    1.73
    mainly
    1.61
     entweder
    1.55
    要么
    1.53
    various
    1.47
    Activations Density 0.524%

    No Known Activations