© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 118696
    Prev
    Next
    INDEX
    Explanations

    programming language keywords

    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
     reputed
    -0.07
    🤴
    -0.07
    within
    -0.07
     famoso
    -0.07
     irrespective
    -0.06
     kwenye
    -0.06
     några
    -0.06
     during
    -0.06
    raintes
    -0.06
    }-
    -0.06
    POSITIVE LOGITS
     wraz
    0.08
    recieve
    0.07
     recieve
    0.07
     ঘাঁটি
    0.07
     recieved
    0.07
     každ
    0.07
    并且
    0.07
     以及
    0.06
     feita
    0.06
    সাথে
    0.06
    Activations Density 0.075%

    No Known Activations