© 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-3-27B
    5. 53-GEMMASCOPE-2-RES-65K
    7. 8501
    Prev
    Next
    INDEX
    Explanations

    family and romantic relationships

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

    model response generation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_53_width_65k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     fuck
    0.83
    Fuck
    0.80
     fucked
    0.78
     fucking
    0.77
     Fuck
    0.77
    🖕
    0.72
     nigga
    0.70
     shit
    0.68
    fuck
    0.68
     dude
    0.67
    POSITIVE LOGITS
     Mommy
    0.80
     hubby
    0.78
     DH
    0.74
     meninas
    0.73
     девочки
    0.72
     Obrig
    0.71
     ragazze
    0.71
     엄마
    0.70
    👭
    0.70
    🩷
    0.70
    Activations Density 0.216%

    No Known Activations