© 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. 118254
    Prev
    Next
    INDEX
    Explanations

    lists and locations

    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
     사건
    -0.07
     отношениях
    -0.06
    采访
    -0.06
     eSIM
    -0.06
     উদ্যোগে
    -0.06
     könnte
    -0.06
    倒是
    -0.06
     उसकी
    -0.06
     случае
    -0.06
     film
    -0.06
    POSITIVE LOGITS
     prepping
    0.07
     hazırl
    0.07
     tools
    0.07
     techniques
    0.07
     vyu
    0.07
     utilisant
    0.06
     utilizar
    0.06
    Tips
    0.06
     crea
    0.06
     Pract
    0.06
    Activations Density 0.004%

    No Known Activations