© 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. 90537
    Prev
    Next
    INDEX
    Explanations

    only, also, either, ever, instead

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

    The neuron fires on common adverbs (e.g. only, also, already, always, first) regardless of their ending.

    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
     again
    -1.28
     подобрать
    -1.27
     of
    -1.24
     furthermore
    -1.10
     altogether
    -1.07
     aspectos
    -1.05
    龊
    -1.04
     moreover
    -0.99
     امریک
    -0.97
     entendimiento
    -0.96
    POSITIVE LOGITS
    ほら
    1.17
     Faça
    1.10
    明日は
    1.08
    マジで
    1.08
    さぁ
    1.07
     zamiast
    1.06
     indien
    1.06
    今度
    1.05
     terke
    1.05
    While
    1.05
    Activations Density 0.117%

    No Known Activations