© 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. 10-GEMMASCOPE-RES-131K
    7. 73000
    Prev
    Next
    INDEX
    Explanations

    sprig

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

    The neuron fires strongly on C/C++ postfix operators—especially post‐increment (“++”) and array subscription (“[]”) tokens.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     &
    -2.23
     {
    -2.22
     
    -2.17
    \
    -2.09
    at
    -1.91
     “
    -1.87
    for
    -1.80
    To
    -1.78
     onderstaande
    -1.70
     lessen
    -1.69
    POSITIVE LOGITS
    𝘕
    2.22
    唞
    2.14
    夲
    2.13
    mpagne
    2.09
     musíte
    2.08
     hlavy
    2.08
     člov
    2.06
     verksamhet
    2.03
    ᨘ
    2.03
    鲧
    2.02
    Activations Density 0.001%

    No Known Activations