© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 121079
    Prev
    Next
    INDEX
    Explanations

    proper names and specific terms

    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
    Negative Logits
    宣布
    -0.06
     announcements
    -0.06
     because
    -0.06
     when
    -0.06
     அப்ப
    -0.06
     fordi
    -0.06
     عندما
    -0.06
    ဦး
    -0.06
     जेव्हा
    -0.06
     когда
    -0.06
    POSITIVE LOGITS
     shrunk
    0.07
     tweaked
    0.06
     tweak
    0.06
    ल्फ़
    0.06
     बेहतरीन
    0.06
     pkt
    0.06
     criter
    0.06
     makeshift
    0.06
    ন্নত
    0.06
     limitless
    0.06
    Activations Density 0.004%

    No Known Activations