© 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. 130622
    Prev
    Next
    INDEX
    Explanations

    On the other hand, meanwhile

    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
     entweder
    -0.06
     서로
    -0.06
     बीजेपी
    -0.06
     stuffs
    -0.06
    ėje
    -0.06
    什么的
    -0.06
     puedas
    -0.06
    ㅏ
    -0.06
     vervolgens
    -0.06
    ヱ
    -0.06
    POSITIVE LOGITS
     hráč
    0.07
     a
    0.06
     how
    0.06
     in
    0.06
     kurang
    0.06
     nasıl
    0.06
    UEFA
    0.06
     significa
    0.05
     réussi
    0.05
     Howell
    0.05
    Activations Density 0.003%

    No Known Activations