© 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. 128854
    Prev
    Next
    INDEX
    Explanations

    Veyron, oxide, clinical, Edwidge

    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
     Spaß
    -0.07
     skept
    -0.06
    credible
    -0.06
     antidepressant
    -0.06
     आघाडी
    -0.06
     neuromuscular
    -0.06
     youth
    -0.06
    쫑
    -0.06
     নারী
    -0.06
     lakes
    -0.06
    POSITIVE LOGITS
    portion
    0.07
     Explore
    0.06
     partly
    0.06
     explor
    0.06
    一半
    0.06
    Explore
    0.06
     explorer
    0.06
    から
    0.06
     kısmı
    0.06
    पूर्व
    0.05
    Activations Density 0.003%

    No Known Activations