© 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. 120008
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions involving coefficients or variables

    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
    Either
    -0.07
     नहीं
    -0.07
    最適な
    -0.07
     nostra
    -0.07
    either
    -0.06
    Basically
    -0.06
    Tidak
    -0.06
     혹은
    -0.06
    ▯
    -0.06
     either
    -0.06
    POSITIVE LOGITS
     annually
    0.06
     PIR
    0.06
     jährlich
    0.06
     ftp
    0.06
    katkan
    0.06
     annual
    0.05
     raising
    0.05
    annual
    0.05
     úlo
    0.05
    tof
    0.05
    Activations Density 0.003%

    No Known Activations