© 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. 116813
    Prev
    Next
    INDEX
    Explanations

    mathematical equations

    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
    HOME
    -0.06
    Ù
    -0.06
     करा
    -0.05
    push
    -0.05
    thel
    -0.05
    nesi
    -0.05
    旳
    -0.05
    <0xE3>
    -0.05
    Dem
    -0.05
     explique
    -0.05
    POSITIVE LOGITS
     rất
    0.07
    感謝
    0.07
     ίδ
    0.07
     zarówno
    0.06
    ασ
    0.06
     produtos
    0.06
     Billion
    0.06
     určit
    0.06
     atât
    0.06
     সবচেয়ে
    0.06
    Activations Density 0.004%

    No Known Activations