© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 65813
    Prev
    Next
    INDEX
    Explanations

    if you conditional statements

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

    The neuron detects second-person conditional prompts beginning with “If you…”

    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
     Bikin
    -1.22
     pantaloni
    -1.21
     Terima
    -1.18
    Отлич
    -1.13
    Leírás
    -1.11
     Desain
    -1.10
    Пусть
    -1.09
     abbigliamento
    -1.09
     kopling
    -1.08
    Наде
    -1.07
    POSITIVE LOGITS
    ,
    1.16
    .
    1.04
    irvana
    1.02
     or
    1.02
     verschillen
    1.00
     \
    1.00
    рина
    0.98
    !
    0.97
     Taq
    0.95
    нг
    0.94
    Activations Density 0.047%

    No Known Activations