© 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. 118171
    Prev
    Next
    INDEX
    Explanations

    LaTeX delimiters and structure

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

    This neuron detects standalone numeric tokens (i.e. sequences of digits).

    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
     in
    -1.11
     having
    -0.99
     heightened
    -0.95
     From
    -0.94
    From
    -0.93
    方がいい
    -0.93
    Having
    -0.91
     specific
    -0.90
     With
    -0.89
     Some
    -0.87
    POSITIVE LOGITS
    ↵
    1.54
     diverses
    1.01
     molti
    0.96
     tâ
    0.89
    spel
    0.88
    Kaieteur
    0.88
     atti
    0.87
    0.86
     quei
    0.85
     wali
    0.85
    Activations Density 0.005%
    No Known Activations