© 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. 117484
    Prev
    Next
    INDEX
    Explanations

    getting various

    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
     efectivos
    -0.07
    最
    -0.07
    一个新的
    -0.06
     efektif
    -0.06
     sadd
    -0.06
    一个
    -0.06
     wealthiest
    -0.06
    中最
    -0.06
    最有
    -0.06
    付属品
    -0.06
    POSITIVE LOGITS
     Getting
    0.08
     getting
    0.07
    various
    0.07
    getting
    0.06
     finner
    0.06
     various
    0.06
     sundry
    0.06
     çeşitli
    0.06
     all
    0.06
    Getting
    0.06
    Activations Density 0.006%

    No Known Activations