© 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. 54061
    Prev
    Next
    INDEX
    Explanations

    comment characters followed by http

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

    The neuron is activated by standalone numeric tokens (large 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
    スポンサーリンク
    -1.12
    轎
    -0.90
    رفة
    -0.88
    ちなみに
    -0.88
    Untuk
    -0.87
    こんな
    -0.85
    Contactez
    -0.85
    ここ
    -0.85
     temática
    -0.85
    Strictly
    -0.85
    POSITIVE LOGITS
       
    1.24
        
    1.05
         
    0.98
    ˗
    0.90
    begin
    0.89
     redeeming
    0.84
     juxtaposition
    0.82
    寐
    0.81
    ```
    0.81
    nachweise
    0.81
    Activations Density 0.281%

    No Known Activations