© 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. 104452
    Prev
    Next
    INDEX
    Explanations

    before, preparation, planning

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

    The neuron is highly responsive to frequent function words—common auxiliaries, pronouns, articles, prepositions, and conjunctions—in running text.

    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
    ecznie
    -1.19
     összefoglal
    -1.06
     sū
    -1.03
    ningarna
    -1.01
     they
    -0.99
     Their
    -0.96
    Within
    -0.92
    -0.91
     within
    -0.90
     összefoglaló
    -0.89
    POSITIVE LOGITS
     before
    1.75
     قبل
    1.53
     preparation
    1.47
     πριν
    1.40
     antes
    1.40
     ennen
    1.38
     sebelum
    1.36
     planning
    1.36
     beforehand
    1.35
     trước
    1.31
    Activations Density 0.057%

    No Known Activations