© 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. 117127
    Prev
    Next
    INDEX
    Explanations

    publishing, making available, submission

    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
    Ệ
    -0.07
    人类
    -0.07
     hizmet
    -0.06
     temporarily
    -0.06
    人類
    -0.06
     perfume
    -0.06
     Humanities
    -0.06
    を生
    -0.06
     احسن
    -0.06
     hehe
    -0.06
    POSITIVE LOGITS
     previous
    0.06
     tidligere
    0.06
    former
    0.06
     выбрали
    0.06
     former
    0.06
     Begriff
    0.06
    formerly
    0.06
     преж
    0.06
     परहेज
    0.06
     পায়ের
    0.06
    Activations Density 0.001%

    No Known Activations