© 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. 32648
    Prev
    Next
    INDEX
    Explanations

    consequence nouns

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

    The main thing this neuron does is detect numeric quantities and measurements (including integers, decimals, and percentages).

    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
    聞いた
    -0.89
    נין
    -0.85
     sowie
    -0.84
     αλλά
    -0.81
    ローチ
    -0.81
     توصیه
    -0.80
    Dalam
    -0.80
    ШЕ
    -0.79
    ھا
    -0.77
    genheiten
    -0.76
    POSITIVE LOGITS
     sehingga
    2.08
     enough
    1.93
     поэтому
    1.92
     hence
    1.69
     therefore
    1.69
     and
    1.49
     thus
    1.46
    enough
    1.43
     donc
    1.38
     Therefore
    1.36
    Activations Density 0.230%

    No Known Activations