© 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. 129807
    Prev
    Next
    INDEX
    Explanations

    cell types

    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
    인데
    -0.06
     grandkids
    -0.06
     Criteria
    -0.06
     grandiose
    -0.06
    父母
    -0.06
     payers
    -0.06
     shoppers
    -0.06
     buyers
    -0.06
     ২টি
    -0.06
     υψη
    -0.06
    POSITIVE LOGITS
     schre
    0.07
    xyl
    0.06
     हमने
    0.06
     improve
    0.06
     Parrot
    0.06
     वितरण
    0.06
    하다고
    0.06
    ত্তর
    0.06
     ultraf
    0.06
    抄
    0.06
    Activations Density 0.003%

    No Known Activations