© 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. 130405
    Prev
    Next
    INDEX
    Explanations

    bone cancer treatment

    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
    妇女
    -0.09
     wanita
    -0.08
     women
    -0.08
     ladies
    -0.08
     жінок
    -0.08
     ženy
    -0.08
     feminina
    -0.07
     lady
    -0.07
     mujer
    -0.07
     Women
    -0.07
    POSITIVE LOGITS
    Student
    0.06
     student
    0.06
     আক্রমণের
    0.06
    VID
    0.06
    remove
    0.05
     konus
    0.05
    ۤ
    0.05
     Student
    0.05
     좋아하는
    0.05
    鉴
    0.05
    Activations Density 0.010%

    No Known Activations