© 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. 128583
    Prev
    Next
    INDEX
    Explanations

    survivors or remission

    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
    .....
    -0.06
    .......
    -0.06
    ......
    -0.06
     transfer
    -0.06
    ........
    -0.06
     destruction
    -0.06
    ..........
    -0.06
    !!!!!!!
    -0.06
    ...........
    -0.06
    POSITIVE LOGITS
     상태
    0.07
    璁
    0.06
    鲷
    0.06
     обычно
    0.06
    每月
    0.06
     Однако
    0.06
    每
    0.06
    sandbox
    0.06
     अब
    0.06
    חש
    0.06
    Activations Density 0.024%

    No Known Activations