© 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. 119571
    Prev
    Next
    INDEX
    Explanations

    first, primary, repeat, different, two

    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
     između
    -0.07
    raad
    -0.06
     између
    -0.06
     cheated
    -0.06
     zwischen
    -0.06
    artic
    -0.06
     Paulista
    -0.06
    ʢ
    -0.06
     حركة
    -0.06
    磴
    -0.05
    POSITIVE LOGITS
     if
    0.07
    essen
    0.06
    anjutan
    0.06
     junior
    0.06
    icrous
    0.06
     If
    0.06
     While
    0.06
     exempl
    0.06
     quadrad
    0.06
     photocon
    0.06
    Activations Density 0.001%

    No Known Activations