© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 116100
    Prev
    Next
    INDEX
    Explanations

    human rights and associated professions

    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
     bereits
    -0.07
     already
    -0.07
     being
    -0.07
    Already
    -0.06
     Already
    -0.06
     расстоя
    -0.06
     noch
    -0.06
     estoy
    -0.06
     כבר
    -0.06
     déjà
    -0.06
    POSITIVE LOGITS
     Reporter
    0.06
    Reporter
    0.06
     ఆర్
    0.06
    因此
    0.06
    تقرير
    0.06
    éditeur
    0.06
     schal
    0.06
    édé
    0.06
     nécessite
    0.06
     necessitates
    0.06
    Activations Density 0.006%

    No Known Activations