© 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. 129128
    Prev
    Next
    INDEX
    Explanations

    WARRANTY;

    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
    JAR
    -0.06
     страте
    -0.06
    ourse
    -0.06
     largo
    -0.06
     använder
    -0.05
    corporate
    -0.05
     luôn
    -0.05
    Suite
    -0.05
     ጎ
    -0.05
    ^{*}=
    -0.05
    POSITIVE LOGITS
    acept
    0.06
    Bounding
    0.06
     quelques
    0.06
    暂时
    0.06
     предлагают
    0.06
    林的
    0.06
     નજી
    0.06
     will
    0.06
     некоторые
    0.06
    可以
    0.06
    Activations Density 0.001%

    No Known Activations