© 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. 127572
    Prev
    Next
    INDEX
    Explanations

    Nice looking pistol, Product Description

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

    The neuron is primarily detecting tokens that contain digits (i.e. numerical strings).

    oai_token-act-pair · o4-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
     más
    -1.86
     for
    -1.72
    ⇹
    -1.64
     If
    -1.62
    ței
    -1.57
    Ꮀ
    -1.57
     mayoría
    -1.56
     demás
    -1.55
    mathrm
    -1.52
    8
    -1.52
    POSITIVE LOGITS
    these
    1.88
     großartige
    1.64
    Zubereitung
    1.63
    Crítica
    1.58
     típica
    1.57
    which
    1.54
     絶
    1.53
     adaptarse
    1.52
    〟
    1.52
     bekannte
    1.51
    Activations Density 0.002%

    No Known Activations