© 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. 117824
    Prev
    Next
    INDEX
    Explanations

    Chinese medicine and neurobehavioral effects

    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
     источник
    -0.08
     листо
    -0.07
     можливість
    -0.07
     ב
    -0.06
     estremamente
    -0.06
    quelle
    -0.06
     Quelle
    -0.06
     توصل
    -0.06
     source
    -0.06
     помещение
    -0.06
    POSITIVE LOGITS
     reinterpret
    0.06
     these
    0.06
     augmented
    0.06
     this
    0.06
     注意
    0.06
     augment
    0.06
    Follow
    0.06
     theſe
    0.06
     knitting
    0.05
    supporting
    0.05
    Activations Density 0.021%

    No Known Activations