© 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. 119512
    Prev
    Next
    INDEX
    Explanations

    administrative and legal contexts

    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
     원래
    -0.06
     estes
    -0.06
     bunların
    -0.06
     questi
    -0.06
    不管
    -0.06
     lst
    -0.06
     ಯಾರ
    -0.06
     €
    -0.06
     xml
    -0.06
     эти
    -0.06
    POSITIVE LOGITS
     дві
    0.07
     тща
    0.06
    矩
    0.06
     EACH
    0.06
     以及
    0.06
     ottim
    0.06
    priv
    0.06
     ডু
    0.06
     shatter
    0.06
     oraz
    0.06
    Activations Density 0.001%

    No Known Activations