© 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-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 129844
    Prev
    Next
    INDEX
    Explanations

    sexuality, romantic attraction, and related actions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    decoderesearch/gemma-4-saes/gemma-4-31b
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Both
    -0.08
    During
    -0.08
     Both
    -0.07
     Preto
    -0.06
     両
    -0.06
     During
    -0.06
     Properties
    -0.06
     incol
    -0.06
    TableAdapter
    -0.06
     visiter
    -0.06
    POSITIVE LOGITS
    全都
    0.06
     joking
    0.06
    言
    0.06
    地に
    0.05
     lubric
    0.05
    ermos
    0.05
     शुरूआत
    0.05
     consape
    0.05
     unsh
    0.05
     relativ
    0.05
    Activations Density 0.006%

    No Known Activations