© 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. 128321
    Prev
    Next
    INDEX
    Explanations

    parenthetical phrases

    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
     illusory
    -0.07
     названия
    -0.07
     named
    -0.07
     dropdown
    -0.06
     ImportError
    -0.06
    情况下
    -0.06
     нормально
    -0.06
     options
    -0.06
     Options
    -0.06
    ৃতি
    -0.06
    POSITIVE LOGITS
     während
    0.07
     during
    0.06
     seeds
    0.06
     ходе
    0.06
     하나의
    0.06
     که
    0.06
     cette
    0.06
     tijdens
    0.06
    单个
    0.06
     that
    0.06
    Activations Density 0.011%

    No Known Activations