© 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. 87015
    Prev
    Next
    INDEX
    Explanations

    as a

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

    The neuron strongly activates on the token “as,” i.e. instances of the conjunction/preposition “as.”

    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
     then
    -1.88
     vainqueur
    -1.65
     these
    -1.65
    TestingModule
    -1.63
    логических
    -1.58
     meur
    -1.56
     Chinois
    -1.53
     donc
    -1.49
     dolu
    -1.47
     Oggi
    -1.46
    POSITIVE LOGITS
    </h5>
    1.79
     in
    1.78
    </h3>
    1.75
    🢒
    1.69
     support
    1.54
     if
    1.44
    </h2>
    1.42
     is
    1.41
     poderia
    1.41
     his
    1.39
    Activations Density 0.109%

    No Known Activations