© 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. 34-GEMMASCOPE-RES-131K
    7. 106471
    Prev
    Next
    INDEX
    Explanations

    numbers following punctuation

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

    The neuron activates on numeric tokens (digits or multi‐digit numbers).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    ῦ
    -1.05
     durables
    -0.87
    了他的
    -0.87
    isenberg
    -0.85
    opter
    -0.81
     stamp
    -0.79
    discuss
    -0.78
    centration
    -0.78
     später
    -0.77
     Condem
    -0.75
    POSITIVE LOGITS
     ytterligare
    0.81
    vás
    0.76
     further
    0.76
     didnt
    0.73
    Dictionary
    0.72
     weiteren
    0.71
     далее
    0.71
     дальше
    0.70
     sweetness
    0.69
     المصرية
    0.68
    Activations Density 0.121%

    No Known Activations