© 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. 128311
    Prev
    Next
    INDEX
    Explanations

    block diagram

    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
    몽
    -0.06
     not
    -0.06
     থেকেও
    -0.06
    ल्
    -0.06
     brilh
    -0.06
    出して
    -0.06
     usando
    -0.05
     tomando
    -0.05
    PORT
    -0.05
     removing
    -0.05
    POSITIVE LOGITS
     Cómo
    0.07
    ociaż
    0.06
    你
    0.06
    atien
    0.06
    iddle
    0.06
    我们
    0.06
    derr
    0.06
    myX
    0.05
     breezes
    0.05
     McManus
    0.05
    Activations Density 0.003%

    No Known Activations