© 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. 128439
    Prev
    Next
    INDEX
    Explanations

    Australian and Australia

    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
    मिट
    -0.07
     orientated
    -0.07
     centred
    -0.06
     focussed
    -0.06
    Acknowledgements
    -0.06
     कार्रवाई
    -0.06
    centred
    -0.06
    võ
    -0.06
    list
    -0.06
     restable
    -0.06
    POSITIVE LOGITS
     olisi
    0.07
    ,【
    0.06
     forecasted
    0.06
     εί
    0.06
    ஸில்
    0.06
     হীর
    0.06
     broom
    0.06
     worrisome
    0.06
     byproduct
    0.06
     సన్ని
    0.06
    Activations Density 0.048%

    No Known Activations