© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 130059
    Prev
    Next
    INDEX
    Explanations

    legal and contractual agreements

    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
     REALLY
    -0.07
     ჩვენ
    -0.06
     wasnt
    -0.06
    really
    -0.06
     really
    -0.06
     Truly
    -0.06
    THER
    -0.06
    १८६
    -0.06
     SURE
    -0.06
    それが
    -0.05
    POSITIVE LOGITS
     peuvent
    0.07
     लै
    0.06
     to
    0.06
     появляются
    0.06
     of
    0.06
     from
    0.06
     spotlight
    0.06
     सोर्स
    0.06
     используются
    0.06
    会让
    0.06
    Activations Density 0.001%

    No Known Activations