© 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. 118391
    Prev
    Next
    INDEX
    Explanations

    likely numbers or sequence completion

    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
     evacu
    -0.07
    ান্
    -0.06
     bahwa
    -0.06
     utiles
    -0.06
     другими
    -0.05
     Ευ
    -0.05
     rằng
    -0.05
     anderen
    -0.05
     частности
    -0.05
     Schools
    -0.05
    POSITIVE LOGITS
     possibly
    0.07
    ?
    0.07
     seemingly
    0.06
     cuáles
    0.06
     tých
    0.06
     mainWindow
    0.06
     samtidigt
    0.06
    မှ
    0.06
     möglicherweise
    0.06
    ？
    0.06
    Activations Density 0.015%

    No Known Activations