© 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. 120608
    Prev
    Next
    INDEX
    Explanations

    asking questions or hypotheses

    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
    nonumber
    -0.06
     reorganization
    -0.06
     essential
    -0.05
    Essential
    -0.05
    dominal
    -0.05
     aktuelle
    -0.05
     oftent
    -0.05
    ␣
    -0.05
    其实
    -0.05
     alertas
    -0.05
    POSITIVE LOGITS
     places
    0.07
     weird
    0.07
     개
    0.07
     nuevo
    0.06
     parts
    0.06
     설명
    0.06
    的一部分
    0.06
    兩
    0.06
     mystery
    0.06
    nieuw
    0.06
    Activations Density 0.066%

    No Known Activations