© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 84034
    Prev
    Next
    INDEX
    Explanations

    used cars

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

    The neuron is triggered by standalone numeric literals (numbers) in code or comments.

    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
    ))\
    -0.90
    ixed
    -0.88
    apimachinery
    -0.86
    lawless
    -0.81
    ISTRO
    -0.81
    aze
    -0.81
    "):
    
    -0.79
    intar
    -0.78
     contesta
    -0.77
    нта
    -0.77
    POSITIVE LOGITS
     lisää
    0.76
            
    0.75
                
    0.74
     smiles
    0.73
     tenths
    0.73
     smile
    0.70
     سرخ
    0.70
    ésor
    0.70
     lovely
    0.69
    sms
    0.69
    Activations Density 0.001%

    No Known Activations