© 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. 22-GEMMASCOPE-RES-131K
    7. 128452
    Prev
    Next
    INDEX
    Explanations

    The neuron fires on explicitly sexual or erotic language (e.g. words referring to nudity, seduction, body parts, and related descriptors).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    sexual content

    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_22/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
    　(
    -1.12
    ❓
    -1.09
     elef
    -1.05
     vins
    -1.05
    ❗️
    -1.03
     VED
    -1.02
     usi
    -1.02
    ❔
    -1.02
    puestas
    -1.02
     aksi
    -1.00
    POSITIVE LOGITS
     wró
    0.96
     процентов
    0.91
     ersetzt
    0.90
    的目光
    0.89
     business
    0.89
     политика
    0.88
    多谢
    0.88
     trzyma
    0.87
     Nachbar
    0.86
     memimpin
    0.85
    Activations Density 0.071%

    No Known Activations