© 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. 116366
    Prev
    Next
    INDEX
    Explanations

    abbreviations followed by specific 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
     candidatura
    -0.06
     llen
    -0.06
    lol
    -0.06
     teht
    -0.06
     lol
    -0.06
     অন্যরা
    -0.06
     η
    -0.06
     horrified
    -0.06
     উদ্বে
    -0.06
     lainnya
    -0.05
    POSITIVE LOGITS
     अपराधियों
    0.06
     não
    0.06
     எல்லா
    0.06
     немно
    0.06
    你们
    0.05
    <sub>
    0.05
    之間
    0.05
     någon
    0.05
    之间
    0.05
     thinks
    0.05
    Activations Density 0.027%

    No Known Activations