© 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. 116924
    Prev
    Next
    INDEX
    Explanations

    other languages

    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
     which
    -0.06
     psychologist
    -0.06
     টুক
    -0.06
     while
    -0.06
     when
    -0.06
    有机会
    -0.06
     hol
    -0.06
    Ber
    -0.05
     заключения
    -0.05
     Mir
    -0.05
    POSITIVE LOGITS
     autres
    0.13
     other
    0.12
     otras
    0.12
     anderen
    0.12
     других
    0.12
     innych
    0.12
    和其他
    0.12
    或其他
    0.11
     अन्य
    0.11
     drugih
    0.11
    Activations Density 0.155%

    No Known Activations