© 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. 117382
    Prev
    Next
    INDEX
    Explanations

    locations

    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
    still
    -0.06
     heap
    -0.06
     still
    -0.06
    ო
    -0.06
    ুলি
    -0.06
    場合の
    -0.06
     sebagai
    -0.06
     संक्रमित
    -0.06
     perc
    -0.05
    মন্দ
    -0.05
    POSITIVE LOGITS
     katt
    0.06
    قط
    0.06
     continuidad
    0.06
    网络的
    0.06
    aturan
    0.06
    Okay
    0.06
     കേ
    0.06
     জল
    0.06
     શક્ય
    0.06
     निः
    0.06
    Activations Density 0.051%

    No Known Activations