© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 103717
    Prev
    Next
    INDEX
    Explanations

    censor, censorship

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

    The neuron is triggered by words and references related to censoring or content censorship.

    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
     Notably
    -2.53
     Perhaps
    -2.44
     Would
    -2.36
     Granted
    -2.34
     Either
    -2.34
     Besides
    -2.27
     Achieving
    -2.27
     Also
    -2.27
     Recently
    -2.27
     Definitely
    -2.19
    POSITIVE LOGITS
    ↵
    4.63
    ientras
    2.20
    ），
    2.19
    蠖
    2.11
    賒
    2.11
     cok
    2.09
    to
    2.08
     vijf
    2.03
    
    2.03
    it
    2.02
    Activations Density 0.004%

    No Known Activations