© 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. 118695
    Prev
    Next
    INDEX
    Explanations

    experimenting with actions or procedures

    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
     विकिरण
    -0.06
    amana
    -0.06
     järjest
    -0.06
    -0.06
     pořád
    -0.05
     auxquels
    -0.05
    在這個
    -0.05
     kaldığımız
    -0.05
    鴻
    -0.05
    gevity
    -0.05
    POSITIVE LOGITS
    Experiment
    0.07
     النص
    0.07
     test
    0.07
    experiment
    0.07
     tervez
    0.06
     testi
    0.06
     experiment
    0.06
     연습
    0.06
    練習
    0.06
     experimenting
    0.06
    Activations Density 0.030%

    No Known Activations