© 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. 34-GEMMASCOPE-RES-131K
    7. 48962
    Prev
    Next
    INDEX
    Explanations

    pornography or child abuse

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     dumbass
    -0.82
    getTable
    -0.82
     alfo
    -0.81
    👗
    -0.80
     DCE
    -0.79
     イベント
    -0.78
     Prejudice
    -0.78
    اریخ
    -0.78
     Cloning
    -0.78
     giang
    -0.77
    POSITIVE LOGITS
     porn
    2.58
     pornography
    2.39
    porn
    1.86
    Porn
    1.81
     Porn
    1.80
    ポル
    1.34
     пор
    1.27
     hardcore
    1.21
     explicit
    1.15
     obscene
    1.15
    Activations Density 0.040%

    No Known Activations