© 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. 119817
    Prev
    Next
    INDEX
    Explanations

    Changes may cause incorrect behavior

    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
    OPT
    -0.06
     cũng
    -0.06
    іга
    -0.06
     OPT
    -0.06
    Also
    -0.06
    ٻ
    -0.06
     різні
    -0.05
     גם
    -0.05
    StringVar
    -0.05
     ሶ
    -0.05
    POSITIVE LOGITS
     olabilir
    0.06
     palpit
    0.06
     had
    0.06
    推动
    0.06
     took
    0.06
     can
    0.06
     colocando
    0.06
    örder
    0.06
    ১০
    0.06
     değerli
    0.06
    Activations Density 0.001%

    No Known Activations