© 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. 120022
    Prev
    Next
    INDEX
    Explanations

    idyllic, romance, butterflies, rosy view

    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
    avoid
    -0.06
     সাক্ষী
    -0.06
     forgotten
    -0.06
     помнить
    -0.06
     struggling
    -0.06
    を起こ
    -0.06
     clums
    -0.06
     அர்த்த
    -0.06
     quelconque
    -0.06
     Avoid
    -0.06
    POSITIVE LOGITS
    WELCOME
    0.07
     patri
    0.06
     পাকিস্তান
    0.06
     sogenannte
    0.06
     לכ
    0.06
     ඇත
    0.06
     serene
    0.05
     idyllic
    0.05
     привет
    0.05
     čist
    0.05
    Activations Density 0.041%

    No Known Activations