© 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. 31324
    Prev
    Next
    INDEX
    Explanations

    code structures or lists

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

    The neuron strongly activates on standalone multi‐digit numbers (numeric literals).

    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
     praktische
    -0.83
    şen
    -0.82
     együtt
    -0.80
     helicóptero
    -0.80
    `]
    -0.79
    точки
    -0.79
    äfte
    -0.78
     heilige
    -0.77
    だけではなく
    -0.76
    antrag
    -0.76
    POSITIVE LOGITS
     even
    0.92
     mostly
    0.84
     mainly
    0.84
           
    0.83
     what
    0.81
     Treff
    0.80
        
    0.80
     даже
    0.78
     primarily
    0.78
         
    0.75
    Activations Density 0.035%

    No Known Activations