© 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. 115524
    Prev
    Next
    INDEX
    Explanations

    designation, discovery, insignificance

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

    The neuron fires on formal metadata or section‐heading labels (e.g. “provisional designation,” “Significance,” “Discovered,” etc.)

    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
     of
    -0.85
    #######
    -0.77
     ansatte
    -0.74
    
    -0.71
     schuhe
    -0.71
    ศึกษา
    -0.71
     subsequent
    -0.71
     zoll
    -0.70
    atly
    -0.70
     årets
    -0.69
    POSITIVE LOGITS
     entdeckt
    0.94
     moitié
    0.87
     fintech
    0.86
    dza
    0.85
     mariée
    0.82
    を発見
    0.81
     discovery
    0.80
    روی
    0.79
    Amor
    0.78
    equalsIgnoreCase
    0.78
    Activations Density 0.000%

    No Known Activations