© 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. 120598
    Prev
    Next
    INDEX
    Explanations

    github.com/ or github.com/path/to/

    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
      
    -0.07
     debemos
    -0.07
     recall
    -0.07
    ımızın
    -0.06
    !!
    -0.06
    orten
    -0.06
    TWO
    -0.06
    ⁢
    -0.06
    !
    -0.06
     veřej
    -0.06
    POSITIVE LOGITS
     a
    0.09
     básicamente
    0.06
     كال
    0.06
    ಡ
    0.06
     an
    0.06
     Basically
    0.06
    一个小
    0.06
    that
    0.06
     kertas
    0.05
    นิด
    0.05
    Activations Density 0.002%

    No Known Activations