© 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. 22-GEMMASCOPE-RES-131K
    7. 71469
    Prev
    Next
    INDEX
    Explanations

    additional setup or refer

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

    The neuron fires on adverbs that signal addition or qualification (e.g. “also,” “maybe”).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     this
    -1.71
     its
    -1.49
     his
    -1.43
     their
    -1.36
     cinto
    -1.31
     Spanyol
    -1.27
    だよね
    -1.27
     کنه
    -1.25
    に行きました
    -1.23
    なのかな
    -1.21
    POSITIVE LOGITS
     localObject
    1.22
    n
    1.17
     is
    1.13
    也可以
    1.09
    但是在
    1.08
    における
    1.07
     أيضًا
    1.07
    e
    1.05
     akkor
    1.04
     явля
    1.03
    Activations Density 0.000%

    No Known Activations