© 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. 22-GEMMASCOPE-RES-131K
    4. 73781
    Prev
    Next
    INDEX
    Explanations

    iterating over collections

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

    The neuron fires strongly on identifiers that name iterable collections or sequence variables (e.g. the collection being looped over or passed as a varargs parameter).

    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
     and
    -1.95
     by
    -1.73
     for
    -1.38
     its
    -1.23
     their
    -1.22
     at
    -1.21
     of
    -1.16
     in
    -1.07
     from
    -1.06
    的一切
    -1.01
    POSITIVE LOGITS
     aplicable
    1.28
     ejus
    1.25
    çando
    1.23
     recomendable
    1.18
    ඍ
    1.17
    "){
    1.16
    forEach
    1.13
    ,‎
    1.13
    形態
    1.10
    																											
    1.07
    Activations Density 0.004%

    No Known Activations