© 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. 129592
    Prev
    Next
    INDEX
    Explanations

    consequence and result of

    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
     그것
    -0.07
     unfamiliar
    -0.06
     universally
    -0.06
     धार
    -0.06
     wholeheartedly
    -0.06
    😰
    -0.06
    Lower
    -0.06
     keduanya
    -0.06
     प्रेमी
    -0.06
     unequiv
    -0.06
    POSITIVE LOGITS
    さんの
    0.07
     move
    0.07
     sẽ
    0.06
     otras
    0.06
    nimi
    0.06
    引起的
    0.06
     möchte
    0.06
     causar
    0.06
     không
    0.06
     ಆದ
    0.06
    Activations Density 0.003%

    No Known Activations