© 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. 129870
    Prev
    Next
    INDEX
    Explanations

    abbreviations or acronyms, foreign 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
     Если
    -0.08
     Nếu
    -0.07
    Если
    -0.07
     cosidd
    -0.07
    Nếu
    -0.06
     Zn
    -0.06
    Jeśli
    -0.06
     podziel
    -0.06
     Якщо
    -0.06
     Wenn
    -0.06
    POSITIVE LOGITS
    :
    0.08
     -
    0.07
     everything
    0.07
    assa
    0.06
     lastly
    0.06
     finally
    0.06
     whole
    0.06
     Un
    0.05
     अंत
    0.05
     what
    0.05
    Activations Density 0.053%

    No Known Activations