© 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. 119534
    Prev
    Next
    INDEX
    Explanations

    will focus on

    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
     sẽ
    -0.08
     will
    -0.07
     if
    -0.07
    だろう
    -0.06
     będ
    -0.06
     буду
    -0.06
     thuyết
    -0.06
     scale
    -0.06
     list
    -0.06
    Being
    -0.06
    POSITIVE LOGITS
     sometimes
    0.07
     actually
    0.07
     parfois
    0.07
     иногда
    0.06
     supposedly
    0.06
     dość
    0.06
     майже
    0.06
    ধবার
    0.06
     настолько
    0.06
     usually
    0.06
    Activations Density 0.006%

    No Known Activations