© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 65450
    Prev
    Next
    INDEX
    Explanations

    romantic relationships and dating

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

    The neuron fires on explicit erotic or pornographic content—words referring to sexual acts, body parts, or overtly sexual situations.

    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
     и
    -1.27
     \&
    -1.25
    。
    -1.22
    приклад
    -1.19
     éven
    -1.16
    ativement
    -1.14
    м
    -1.14
     autre
    -1.13
    titial
    -1.09
    fficking
    -1.09
    POSITIVE LOGITS
    よな
    1.48
     permesso
    1.23
     conosce
    1.23
     trasforma
    1.22
    horabuena
    1.19
     utilizza
    1.16
    恐れ
    1.15
    鵟
    1.15
    чування
    1.11
     chiunque
    1.09
    Activations Density 0.072%

    No Known Activations