© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 83078
    Prev
    Next
    INDEX
    Explanations

    all those

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

    The neuron consistently activates on the word “All” (especially when it begins a clause).

    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
    ierungs
    -1.25
    zeitung
    -1.09
    atique
    -1.09
    leggio
    -1.09
     bytu
    -1.08
    πάρχ
    -1.04
     chaqueta
    -1.02
     några
    -1.02
    ленность
    -1.02
    !*\
    -1.02
    POSITIVE LOGITS
     of
    3.06
     this
    2.20
     these
    1.93
     you
    1.91
     that
    1.80
     those
    1.59
     they
    1.48
     it
    1.43
     else
    1.41
     we
    1.39
    Activations Density 0.032%

    No Known Activations