© 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. 119466
    Prev
    Next
    INDEX
    Explanations

    "Gap"

    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
     Economics
    -0.06
    عاية
    -0.06
    、
    -0.06
     If
    -0.06
     economics
    -0.06
    including
    -0.06
     postup
    -0.06
     представления
    -0.06
     aspects
    -0.05
     cirk
    -0.05
    POSITIVE LOGITS
     почти
    0.07
     на
    0.07
     практически
    0.07
    を
    0.07
     огром
    0.07
     намного
    0.06
     вели
    0.06
     любой
    0.06
     гораздо
    0.06
     по
    0.06
    Activations Density 0.115%

    No Known Activations