© 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. 129245
    Prev
    Next
    INDEX
    Explanations

    ethnic groups, loans, design, location, ownership, secret units

    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
    nobody
    -0.07
     nobody
    -0.07
     não
    -0.07
     nicht
    -0.07
     tidak
    -0.06
     никто
    -0.06
     không
    -0.06
     timbers
    -0.06
     general
    -0.05
    supporting
    -0.05
    POSITIVE LOGITS
    Lip
    0.06
     azonban
    0.06
     anywhere
    0.06
    こうした
    0.06
     migr
    0.06
     Exposure
    0.06
    leys
    0.06
     fix
    0.06
     gemeinsamen
    0.06
     الوصول
    0.06
    Activations Density 0.001%

    No Known Activations