© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 130955
    Prev
    Next
    INDEX
    Explanations

    contrasting sentiments or evaluations

    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
     però
    -0.09
     jedoch
    -0.08
     but
    -0.07
     nhưng
    -0.07
     όμως
    -0.07
     warning
    -0.07
     however
    -0.07
    但
    -0.07
     strides
    -0.07
    但也
    -0.07
    POSITIVE LOGITS
     liten
    0.06
    ោក
    0.06
     about
    0.06
    regions
    0.06
     여기에
    0.06
     bunu
    0.06
     each
    0.06
    態
    0.06
     joka
    0.06
     operation
    0.06
    Activations Density 0.009%

    No Known Activations