© 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. 10-GEMMASCOPE-RES-131K
    7. 45633
    Prev
    Next
    INDEX
    Explanations

    Saturday Night

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

    The neuron responds to numeric tokens—version numbers, bug/issue IDs, dates, and other standalone 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_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     for
    -1.51
     commonly
    -1.46
     primarily
    -1.46
     Those
    -1.45
     ག
    -1.43
    箝
    -1.41
     ར
    -1.41
     used
    -1.40
     ALWAYS
    -1.38
     because
    -1.38
    POSITIVE LOGITS
     différents
    1.63
    ㌘
    1.56
    actéristi
    1.56
    皷
    1.55
    ྵ
    1.52
    レモン
    1.49
    ⅿ
    1.45
     nacht
    1.38
     redução
    1.38
     magnific
    1.37
    Activations Density 0.045%

    No Known Activations