© 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. 119725
    Prev
    Next
    INDEX
    Explanations

    morphometrics, devices

    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
     Акысыз
    -0.06
    犯罪
    -0.06
     বোঝার
    -0.06
     значення
    -0.06
     ameryka
    -0.06
     მთავ
    -0.06
     beggar
    -0.06
    剃
    -0.05
     православ
    -0.05
     Criminal
    -0.05
    POSITIVE LOGITS
     symposium
    0.07
    深入
    0.07
     akin
    0.07
    就像
    0.06
     Castro
    0.06
     enthusiast
    0.06
     seminar
    0.06
    你有
    0.06
     engaging
    0.06
     جزء
    0.06
    Activations Density 0.011%

    No Known Activations