© 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. 116556
    Prev
    Next
    INDEX
    Explanations

    league cup sampling Protestant holders

    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
    两
    -0.07
     with
    -0.06
     leurs
    -0.06
     combinations
    -0.06
     ligeramente
    -0.06
    Samsung
    -0.06
    Their
    -0.06
    和
    -0.06
     iPad
    -0.05
     sometimes
    -0.05
    POSITIVE LOGITS
    wechsl
    0.06
     porque
    0.06
     потому
    0.06
     나오고
    0.06
     মারাত্মক
    0.06
     trouvent
    0.06
     приносит
    0.06
    ﺻ
    0.06
    quer
    0.06
     அதனை
    0.06
    Activations Density 0.001%

    No Known Activations