© 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. 129546
    Prev
    Next
    INDEX
    Explanations

    sub-Saharan Africa

    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
     hubo
    -0.07
     정리
    -0.06
     არს
    -0.06
     정상
    -0.06
     habido
    -0.06
     उपलब्ध
    -0.06
     공유
    -0.06
     большую
    -0.06
    国有
    -0.06
     조금
    -0.06
    POSITIVE LOGITS
    étique
    0.06
    kanen
    0.06
     seule
    0.06
     presumptive
    0.06
    últ
    0.06
    ickets
    0.05
     doigts
    0.05
     unica
    0.05
    手続き
    0.05
    chool
    0.05
    Activations Density 0.001%

    No Known Activations