© 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. 32714
    Prev
    Next
    INDEX
    Explanations

    second plate

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

    The neuron activates on numeric tokens (numbers, counts, or numeric labels) in the text.

    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
    esía
    -0.87
    Sometimes
    -0.84
    Usually
    -0.82
    ("/",
    -0.79
     clásica
    -0.77
    oplayer
    -0.76
     pungkasnya
    -0.76
    ಏ
    -0.76
    Generally
    -0.75
    موس
    -0.75
    POSITIVE LOGITS
    gemaakt
    1.02
    ीन
    0.87
    ene
    0.81
    zkod
    0.81
     ブルゾン
    0.79
    踝
    0.79
    εν
    0.77
    tał
    0.75
     adesso
    0.74
     durante
    0.74
    Activations Density 0.006%

    No Known Activations