© 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. 129537
    Prev
    Next
    INDEX
    Explanations

    states and cities

    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
     pozost
    -0.07
    Cel
    -0.06
     remain
    -0.06
     ني
    -0.06
     Dob
    -0.06
    ghe
    -0.06
    Christ
    -0.06
     Please
    -0.06
     distal
    -0.05
    Dob
    -0.05
    POSITIVE LOGITS
    rapport
    0.07
     líquido
    0.07
     hígado
    0.06
     saldo
    0.06
     fyrir
    0.06
     вспо
    0.06
    িয়ান
    0.06
    めちゃ
    0.06
    maturity
    0.06
     slated
    0.06
    Activations Density 0.002%

    No Known Activations