© 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. 129856
    Prev
    Next
    INDEX
    Explanations

    code blocks

    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
     exciting
    -0.07
     wonderful
    -0.07
     muchos
    -0.06
     wielu
    -0.06
     mnog
    -0.06
     or
    -0.06
     numerose
    -0.06
     many
    -0.06
     including
    -0.06
     ইচ্ছে
    -0.06
    POSITIVE LOGITS
    쨰
    0.06
    其他
    0.06
    Other
    0.06
     каж
    0.06
    opod
    0.06
    Community
    0.06
     двумя
    0.06
    ায়া
    0.06
    ITY
    0.06
     Arth
    0.06
    Activations Density 0.002%

    No Known Activations