© 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. 118282
    Prev
    Next
    INDEX
    Explanations

    contrastive conjunctions like "while" and "but"

    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
    この
    -0.07
    दूसरी
    -0.07
    acuse
    -0.06
     shirts
    -0.06
     यह
    -0.06
    }-
    -0.06
     analysed
    -0.06
    क्यों
    -0.06
     všet
    -0.06
     suggested
    -0.06
    POSITIVE LOGITS
    未必
    0.07
    칠
    0.06
     вовсе
    0.06
     proponents
    0.06
     propia
    0.06
    ではありません
    0.06
     hely
    0.06
    并不是
    0.06
     úpl
    0.06
     may
    0.06
    Activations Density 0.012%

    No Known Activations