© 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. 129172
    Prev
    Next
    INDEX
    Explanations

    length and format of creative works

    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
     группу
    -0.07
     grupo
    -0.07
     그룹
    -0.07
     группы
    -0.06
     którą
    -0.06
     හො
    -0.06
     Grupo
    -0.06
    グループ
    -0.06
     ప్రశ్
    -0.06
     group
    -0.06
    POSITIVE LOGITS
     cementing
    0.07
     meticulous
    0.06
     intricate
    0.06
     ওয়েস্ট
    0.06
    まい
    0.06
    teles
    0.06
     synthesizing
    0.06
     inú
    0.06
     rhiz
    0.05
     acumul
    0.05
    Activations Density 0.006%

    No Known Activations