© 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. 128368
    Prev
    Next
    INDEX
    Explanations

    used herein or hereafter

    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
    ccncc
    -0.06
     vytvá
    -0.06
    㻁
    -0.06
    䢌
    -0.06
     맡
    -0.05
     EF
    -0.05
    㻴
    -0.05
    每一次
    -0.05
     która
    -0.05
     Find
    -0.05
    POSITIVE LOGITS
     altri
    0.07
     otros
    0.07
     proclaims
    0.07
     offizi
    0.07
     anderen
    0.07
     blatant
    0.07
     it
    0.07
     lauded
    0.06
     triumphant
    0.06
     другом
    0.06
    Activations Density 0.002%

    No Known Activations