© 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. 129032
    Prev
    Next
    INDEX
    Explanations

    sets of mathematical objects

    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
     effektiv
    -0.06
     Certains
    -0.06
     улуч
    -0.06
    เหมาะ
    -0.06
     certe
    -0.06
    ผ่าน
    -0.06
    جموع
    -0.06
    业界
    -0.06
     unui
    -0.06
     Associate
    -0.06
    POSITIVE LOGITS
     Terrorism
    0.07
     Then
    0.06
     Afterwards
    0.06
     between
    0.06
     then
    0.06
     서로
    0.06
     relem
    0.06
     Between
    0.06
    then
    0.06
     perhaps
    0.06
    Activations Density 0.009%

    No Known Activations