© 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. 45726
    Prev
    Next
    INDEX
    Explanations

    home court advantage

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

    This neuron activates on numerical tokens (digits and decimal numbers).

    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
    м
    -1.88
     "
    -1.87
    theless
    -1.70
     OGSÅ
    -1.68
    何况
    -1.67
    に
    -1.67
    但这
    -1.66
    ╟
    -1.66
    ですが
    -1.66
     как
    -1.65
    POSITIVE LOGITS
    </h1>
    2.06
    0
    1.95
    躄
    1.80
    ところです
    1.77
    </h2>
    1.76
     nowy
    1.68
     awe
    1.67
     Todas
    1.66
     proud
    1.63
     encontrar
    1.63
    Activations Density 0.002%

    No Known Activations