© 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. 128579
    Prev
    Next
    INDEX
    Explanations

    (not

    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
     or
    -0.08
     یا
    -0.07
     名称
    -0.06
     или
    -0.06
    的意思
    -0.06
     atau
    -0.06
    名称
    -0.06
     ఉండ
    -0.06
    ிழ
    -0.06
     શિક્ષ
    -0.06
    POSITIVE LOGITS
    στή
    0.06
    不同的
    0.06
    ორე
    0.06
     DIFFERENT
    0.06
     entonces
    0.06
    телей
    0.06
    thed
    0.06
     Universo
    0.05
     different
    0.05
    CONST
    0.05
    Activations Density 0.003%

    No Known Activations