© 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-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 116494
    Prev
    Next
    INDEX
    Explanations

    anticoagulants, heparin, hemoglobin, loading, collecting

    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
    urrent
    -0.06
     Chanc
    -0.05
    нный
    -0.05
     seaside
    -0.05
    ਤਾ
    -0.05
     सोर्स
    -0.05
    洁
    -0.05
    Bed
    -0.05
     geograf
    -0.05
     бед
    -0.05
    POSITIVE LOGITS
     Williamson
    0.07
     ضبط
    0.06
     прогно
    0.06
     informatie
    0.06
     gewährle
    0.06
     hoop
    0.06
     instead
    0.06
     nahilalakip
    0.06
    instead
    0.06
     பாரம்பரிய
    0.06
    Activations Density 0.001%

    No Known Activations