© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 78564
    Prev
    Next
    INDEX
    Explanations

    As + verb/situation

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

    This neuron strongly activates on the subordinating conjunction “As” when it appears at the start of a clause or sentence.

    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
    highlighted
    -1.08
    shown
    -1.04
    currently
    -1.03
    launched
    -1.02
    once
    -1.00
     ModelExpression
    -0.98
    glob
    -0.93
    yue
    -0.93
    venidos
    -0.92
    nicy
    -0.92
    POSITIVE LOGITS
     if
    2.09
     luck
    1.52
     often
    1.44
     could
    1.41
     suele
    1.38
     tends
    1.38
     might
    1.34
     usually
    1.30
     is
    1.24
     any
    1.24
    Activations Density 0.025%

    No Known Activations