© 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. 119448
    Prev
    Next
    INDEX
    Explanations

    information & plans

    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
    loé
    -0.07
     you
    -0.06
     نہیں
    -0.06
    只能
    -0.06
    だけ
    -0.06
     आपको
    -0.06
    يدك
    -0.06
    nsics
    -0.06
     પણ
    -0.06
     Zombie
    -0.06
    POSITIVE LOGITS
    স্‌
    0.07
    若是
    0.06
     schneller
    0.06
    新的
    0.06
     계획
    0.06
     a
    0.06
     clearer
    0.06
    Information
    0.06
     plan
    0.06
     information
    0.06
    Activations Density 0.007%

    No Known Activations