© 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. 129461
    Prev
    Next
    INDEX
    Explanations

    last, justification, smooth, sclerosis

    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
     increasingly
    -0.09
     increasing
    -0.06
     preventing
    -0.06
     similarities
    -0.06
     carefree
    -0.06
     skeletal
    -0.06
     progressively
    -0.06
     both
    -0.06
     unique
    -0.06
    越来越多
    -0.06
    POSITIVE LOGITS
     마지막
    0.07
     does
    0.07
     disponible
    0.07
     ਲੋ
    0.07
    最後に
    0.07
     Commonly
    0.07
     lastly
    0.07
     odpowied
    0.07
     última
    0.07
     очень
    0.06
    Activations Density 0.001%

    No Known Activations