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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 98254
    Prev
    Next
    INDEX
    Explanations

    code ending punctuation

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

    The neuron primarily responds to any token containing digits (numeric literals or symbols with 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
     or
    -1.04
    Finally
    -0.97
    Lastly
    -0.96
     Usually
    -0.94
    Usually
    -0.93
     ONLY
    -0.93
     make
    -0.93
     will
    -0.91
     if
    -0.90
     has
    -0.88
    POSITIVE LOGITS
     faid
    1.18
     noft
    1.17
     notwendig
    1.12
     pivotal
    1.11
     molti
    1.08
     vibrant
    1.06
       
    1.06
     gän
    1.05
     poft
    1.04
     vastly
    1.02
    Activations Density 0.075%

    No Known Activations