© 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. 119410
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     careless
    -0.07
     actuality
    -0.07
     carelessly
    -0.06
    軛
    -0.06
     शुरू
    -0.06
    とにかく
    -0.06
     Booklet
    -0.06
    സ
    -0.06
     Стре
    -0.05
    valent
    -0.05
    POSITIVE LOGITS
     önemli
    0.07
     but
    0.07
    이지만
    0.06
     paljon
    0.06
    と思いますが
    0.06
     ausdr
    0.06
     že
    0.06
     hogy
    0.06
     enggak
    0.06
    扮
    0.06
    Activations Density 0.000%

    No Known Activations