© 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. 99475
    Prev
    Next
    INDEX
    Explanations

    breaking laws or rights

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

    The neuron is triggered by words related to violations (e.g., “violate,” “violations,” “violating”).

    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
    )
    -2.00
    </h2>
    -1.64
    lencia
    -1.62
     symbolize
    -1.59
     a
    -1.59
     Number
    -1.58
     Dessa
    -1.57
    合物
    -1.57
    閙
    -1.55
    殲
    -1.51
    POSITIVE LOGITS
    2
    2.11
    ↵
    2.05
    3
    1.95
    5
    1.74
    Nazwa
    1.73
    覘
    1.70
    媜
    1.70
    7
    1.69
     sportivo
    1.62
    ᳝
    1.60
    Activations Density 0.018%

    No Known Activations