© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 130442
    Prev
    Next
    INDEX
    Explanations

    version/edition indicators

    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
    热水
    -0.07
     reinforcing
    -0.06
     атмос
    -0.06
     seperti
    -0.06
     ඔහුගේ
    -0.06
     heartwarming
    -0.06
    ╅
    -0.06
     reinforces
    -0.06
     hospitable
    -0.06
     ඔහු
    -0.06
    POSITIVE LOGITS
     プロ
    0.06
    স্তে
    0.06
     Many
    0.06
    Many
    0.06
     but
    0.06
    பல
    0.05
    same
    0.05
     ಹಲ
    0.05
     då
    0.05
     夜
    0.05
    Activations Density 0.003%

    No Known Activations