© 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. 119543
    Prev
    Next
    INDEX
    Explanations

    words starting with 'a' followed by 'nd'

    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
     Miscellaneous
    -0.07
     версии
    -0.06
     Мы
    -0.06
    pictured
    -0.06
     المجال
    -0.06
     এরপর
    -0.06
    অথ
    -0.06
     我的
    -0.06
     możliwość
    -0.06
     অথবা
    -0.06
    POSITIVE LOGITS
     ‘
    0.06
     तत्काल
    0.06
     ehrlich
    0.06
    越多
    0.06
     ব্রাহ্ম
    0.06
     정도로
    0.06
    adine
    0.06
     ந
    0.05
     intervenir
    0.05
    by
    0.05
    Activations Density 0.001%

    No Known Activations