© 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. 116746
    Prev
    Next
    INDEX
    Explanations

    economic and societal burden

    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
     consisting
    -0.07
     praktik
    -0.06
     ioutil
    -0.06
     kondisi
    -0.06
     භාවිත
    -0.06
     dangerous
    -0.06
     oblivious
    -0.06
     propria
    -0.06
     disagrees
    -0.06
     berbahaya
    -0.06
    POSITIVE LOGITS
    platforms
    0.07
     platforms
    0.06
    victim
    0.06
     Platforms
    0.06
    LAW
    0.06
     দ্বীপ
    0.06
     after
    0.05
     automáticamente
    0.05
     plataformas
    0.05
     hotspot
    0.05
    Activations Density 0.007%

    No Known Activations