© 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. 10-GEMMASCOPE-RES-131K
    7. 14430
    Prev
    Next
    INDEX
    Explanations

    official documents, licenses, passports, ID cards

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

    The neuron activates on mentions of licenses or licensing (e.g., driver’s licenses, ID cards, and related licensing terms).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     They
    -1.79
    re
    -1.74
    st
    -1.66
    E
    -1.59
    ds
    -1.55
    vi
    -1.54
    </h5>
    -1.53
    芣
    -1.47
    ches
    -1.46
    ts
    -1.45
    POSITIVE LOGITS
    
    1.70
     expandir
    1.55
    　　「
    1.49
     bloquear
    1.48
     reproducir
    1.48
     acompañada
    1.47
     acrílico
    1.47
     destrucción
    1.46
    onsored
    1.45
     reemplazar
    1.43
    Activations Density 0.008%

    No Known Activations