© 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. 84464
    Prev
    Next
    INDEX
    Explanations

    ass / butt

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

    This neuron is triggered by occurrences of “ass” (whether referring to buttocks, sexual content, or used in insults).

    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
    趼
    -3.14
    0
    -2.52
     bekom
    -2.45
    Ꭽ
    -2.38
    ཫ
    -2.30
    但却
    -2.27
     zubehör
    -2.27
    囖
    -2.20
     verdient
    -2.19
    鹮
    -2.19
    POSITIVE LOGITS
    }
    2.84
    nessy
    2.61
     или
    2.56
    หรือ
    2.50
    
    2.48
    ᠂
    2.33
    ꜆
    2.28
     padx
    2.16
    例えば
    2.13
     reconcile
    2.13
    Activations Density 0.006%

    No Known Activations