© 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. 130344
    Prev
    Next
    INDEX
    Explanations

    list item separators

    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
     sati
    -0.07
     stabilizes
    -0.06
    私たち
    -0.05
    さんが
    -0.05
     infl
    -0.05
    ക്ഷണ
    -0.05
    分け
    -0.05
     ours
    -0.05
     twitch
    -0.05
    佅
    -0.05
    POSITIVE LOGITS
     konc
    0.07
     Doing
    0.06
     RIGHT
    0.06
     beginnings
    0.06
     Frankly
    0.06
     concert
    0.06
     ebenso
    0.06
     Dara
    0.06
     healer
    0.06
     fraternal
    0.06
    Activations Density 0.001%

    No Known Activations