© 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. 22648
    Prev
    Next
    INDEX
    Explanations

    import statements

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

    The neuron is detecting numeric tokens (numbers or numeric literals) in the code.

    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
     The
    -1.99
     ‘
    -1.96
    A
    -1.80
    out
    -1.75
    T
    -1.74
    S
    -1.66
    E
    -1.64
    we
    -1.63
    D
    -1.62
     via
    -1.61
    POSITIVE LOGITS
     and
    1.93
    และ
    1.70
    aları
    1.56
    kaç
    1.54
     kompati
    1.51
     osoba
    1.48
     esimer
    1.47
    Bisa
    1.47
    örü
    1.44
     najdete
    1.44
    Activations Density 0.031%

    No Known Activations