© 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. 72098
    Prev
    Next
    INDEX
    Explanations

    the [title/role]

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

    The neuron detects numeric tokens, especially numbers (including decimals) 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_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     innych
    -1.80
    熥
    -1.60
    蚰
    -1.59
    鸲
    -1.57
    aży
    -1.52
    earned
    -1.52
     다른
    -1.52
    烀
    -1.51
    螃
    -1.50
    knows
    -1.49
    POSITIVE LOGITS
     a
    1.77
     and
    1.76
     at
    1.74
     an
    1.73
    </h1>
    1.57
     just
    1.47
     who
    1.42
     president
    1.41
        
    1.39
     unrelenting
    1.39
    Activations Density 0.059%

    No Known Activations