© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 64532
    Prev
    Next
    INDEX
    Explanations

    Q, May, or colons

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

    The neuron activates on numeric literals (especially decimal numbers).

    oai_token-act-pair · o4-mini
    Triggered 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
    Negative Logits
    Informasi
    -1.23
    ♪♪
    -1.16
    Fitur
    -1.15
    Probably
    -1.14
    Вариант
    -1.12
    Maybe
    -1.11
    Они
    -1.10
     eventuell
    -1.10
    也很
    -1.07
    Langkah
    -1.07
    POSITIVE LOGITS
     such
    1.05
    譁
    1.02
     in
    1.02
     whose
    1.01
     pełni
    1.00
    cultura
    1.00
    kannten
    0.99
    咙
    0.99
     reconnu
    0.99
     Breite
    0.99
    Activations Density 0.001%

    No Known Activations