© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 119447
    Prev
    Next
    INDEX
    Explanations

    numbers and words

    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
    awsze
    -0.06
     independent
    -0.06
     always
    -0.06
     مستقل
    -0.06
     কতকগুলি
    -0.06
    их
    -0.05
    nač
    -0.05
     tidak
    -0.05
     независи
    -0.05
     not
    -0.05
    POSITIVE LOGITS
     sowohl
    0.07
     τόσο
    0.07
     Furthermore
    0.06
     により
    0.06
     primeras
    0.06
     Nonetheless
    0.06
     zarówno
    0.06
     Moreover
    0.06
     zowel
    0.06
     tanto
    0.06
    Activations Density 0.004%

    No Known Activations