© 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. 119229
    Prev
    Next
    INDEX
    Explanations

    achieving maximally

    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
     without
    -0.07
     pozw
    -0.07
     ohne
    -0.06
     jefe
    -0.06
     veramente
    -0.06
     facilmente
    -0.06
     permiso
    -0.06
     ১১
    -0.06
     tanpa
    -0.06
     gebruiken
    -0.06
    POSITIVE LOGITS
     möglichst
    0.09
    尽可能
    0.08
     최대한
    0.08
    尽量
    0.07
     buscan
    0.07
     somehow
    0.06
     satur
    0.06
    ukti
    0.06
    寻找
    0.06
     matchup
    0.06
    Activations Density 0.043%

    No Known Activations