© 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. 130154
    Prev
    Next
    INDEX
    Explanations

    patients had medical conditions

    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
     usually
    -0.07
     кілько
    -0.07
    usually
    -0.07
     பெரும்பாலும்
    -0.06
     двох
    -0.06
    往往
    -0.06
     종류
    -0.06
    兩
    -0.06
     prosthesis
    -0.06
     δύο
    -0.06
    POSITIVE LOGITS
     previous
    0.07
     eftersom
    0.06
     más
    0.06
     estaba
    0.06
     ранее
    0.06
     estaban
    0.06
     standard
    0.06
     fue
    0.06
     tidligere
    0.06
     مزید
    0.06
    Activations Density 0.040%

    No Known Activations