© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 31785
    Prev
    Next
    INDEX
    Explanations

    code and programming syntax

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

    The neuron is primarily detecting numeric tokens (literal numbers) in the 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
     correctes
    -0.91
     Если
    -0.90
     После
    -0.90
    
    -0.86
    seks
    -0.85
     възможно
    -0.84
     Чтобы
    -0.84
    ᳝
    -0.83
    ettet
    -0.82
     Под
    -0.81
    POSITIVE LOGITS
     مختلف
    0.88
     estrema
    0.85
    Thoughts
    0.85
     aufgeführt
    0.84
     Erschein
    0.81
    シャレ
    0.80
     solch
    0.80
     fremden
    0.79
     浴室
    0.79
    Zp
    0.78
    Activations Density 0.041%

    No Known Activations