© 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. 7172
    Prev
    Next
    INDEX
    Explanations

    list and collection types

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

    This neuron responds to Scala collection‐API calls—tokens involved in chaining methods on sequences (e.g. grouped, to, extract on Seq) rather than ordinary 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_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
     Gilman
    -0.81
     wszystko
    -0.81
    DataColumn
    -0.76
     (\%)
    -0.75
    ChatColor
    -0.72
    Imgs
    -0.71
    irmingham
    -0.71
    lenül
    -0.71
     getIndex
    -0.71
     ~(
    -0.70
    POSITIVE LOGITS
     list
    2.95
     List
    2.66
     Iterable
    2.64
    List
    2.64
    Iterable
    2.61
     IEnumerable
    2.36
     collection
    2.25
     iterable
    2.25
    IEnumerable
    2.17
    ArrayList
    2.09
    Activations Density 0.087%

    No Known Activations