© 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. 16504
    Prev
    Next
    INDEX
    Explanations

    file path and code snippets

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

    The neuron is triggered by numeric tokens—especially version numbers or other digit-containing strings.

    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
     worse
    -1.32
     πιο
    -1.22
    txt
    -1.22
    muñ
    -1.20
    なもの
    -1.20
    ımı
    -1.18
     ją
    -1.18
    étique
    -1.18
    ostringstream
    -1.18
     intensa
    -1.08
    POSITIVE LOGITS
     Seorang
    1.11
    espero
    1.09
     Secara
    1.06
     Ternyata
    1.05
     Kedua
    1.05
     verwendeten
    1.05
     Penggunaan
    1.05
     използ
    1.04
    Aqui
    1.04
     that
    1.04
    Activations Density 0.001%

    No Known Activations