© 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. 119878
    Prev
    Next
    INDEX
    Explanations

    remake, sequel, cover, adaptation

    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
     définitive
    -0.06
    എ
    -0.06
     опреде
    -0.06
     വാങ്ങ
    -0.06
     nueva
    -0.06
     recommended
    -0.06
     module
    -0.06
     môžete
    -0.06
     završ
    -0.06
     пере
    -0.06
    POSITIVE LOGITS
    reports
    0.06
     reports
    0.06
     основном
    0.06
     Reports
    0.06
     ہمیں
    0.06
     SignUp
    0.06
     گزارش
    0.06
     pressures
    0.06
    ontrol
    0.06
     emptiness
    0.05
    Activations Density 0.016%

    No Known Activations