© 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. 130194
    Prev
    Next
    INDEX
    Explanations

    US states

    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
     aimed
    -0.07
    ‐
    -0.06
     ਵਿੱਚ
    -0.06
     المحلية
    -0.06
     tops
    -0.05
    well
    -0.05
     least
    -0.05
     businesses
    -0.05
     reflected
    -0.05
    лық
    -0.05
    POSITIVE LOGITS
    大量
    0.07
     hampir
    0.07
     logam
    0.06
    izacin
    0.06
     tekanan
    0.06
     Gibraltar
    0.06
     нередко
    0.06
     copious
    0.06
    金属
    0.06
     метал
    0.06
    Activations Density 0.003%

    No Known Activations