© 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. 128307
    Prev
    Next
    INDEX
    Explanations

    origins oflocations ofcountries of

    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
     showing
    -0.07
     attivo
    -0.07
     बटे
    -0.07
    Classification
    -0.07
    showing
    -0.07
     prostaglandins
    -0.06
     deleting
    -0.06
     Classification
    -0.06
     classificação
    -0.06
     कंट
    -0.06
    POSITIVE LOGITS
    kušen
    0.06
     promises
    0.06
     столи
    0.06
     mı
    0.06
    ү
    0.05
     мла
    0.05
    cities
    0.05
     সম্ভবত
    0.05
    에서
    0.05
     ú
    0.05
    Activations Density 0.001%

    No Known Activations