© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 57693
    Prev
    Next
    INDEX
    Explanations

    numbers after punctuation

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

    The neuron fires on numeric literal tokens (i.e. numbers appearing in code or text).

    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
     one
    -1.14
     that
    -1.11
     翔
    -1.04
    Since
    -1.02
     first
    -1.01
     virš
    -1.00
     in
    -0.98
    Zubereitung
    -0.96
    Nearly
    -0.96
    Usually
    -0.95
    POSITIVE LOGITS
     secondly
    1.06
     zweiten
    0.97
    Secondly
    0.95
     twain
    0.92
    第二个
    0.92
    两种
    0.85
     zweimal
    0.85
     second
    0.85
     wunder
    0.85
     weiterer
    0.85
    Activations Density 0.077%

    No Known Activations