© 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. 116497
    Prev
    Next
    INDEX
    Explanations

    newly recognized enlisted

    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
     Lista
    -0.06
     lista
    -0.06
     Airtel
    -0.06
     אבל
    -0.06
     Leicester
    -0.06
     অথচ
    -0.06
     我們
    -0.06
    cemos
    -0.06
    我们将
    -0.06
     Bring
    -0.05
    POSITIVE LOGITS
     newly
    0.08
     nuevos
    0.06
     newfound
    0.06
     الجديد
    0.06
    仍
    0.06
     ploy
    0.06
     അദ്ദേഹ
    0.06
     Founders
    0.06
     नए
    0.06
     नये
    0.06
    Activations Density 0.131%

    No Known Activations