© 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. 24987
    Prev
    Next
    INDEX
    Explanations

    Kota Tinggi Museum

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

    The neuron is detecting numeric tokens (digits and numeric strings, such as version numbers or IDs).

    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
     calça
    -1.48
     vannak
    -1.45
    🫶
    -1.41
    ˂
    -1.39
    様な
    -1.39
    ☀️
    -1.38
    mousse
    -1.38
    bilan
    -1.38
     joyas
    -1.36
     bluza
    -1.36
    POSITIVE LOGITS
    は
    1.63
    そういった
    1.55
    が
    1.49
    ですが
    1.48
     turbul
    1.45
    があり
    1.45
    である
    1.42
    OBJETIVO
    1.41
    CAPÍTULO
    1.38
    もしか
    1.38
    Activations Density 0.003%

    No Known Activations