© 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. 118215
    Prev
    Next
    INDEX
    Explanations

    request

    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
     Macdonald
    -0.06
    borrow
    -0.06
    ческая
    -0.06
    人も
    -0.06
     Э
    -0.06
    шая
    -0.06
     დროს
    -0.06
    दों
    -0.06
    uć
    -0.05
     autonomia
    -0.05
    POSITIVE LOGITS
    Those
    0.08
     those
    0.07
    ইয়া
    0.06
     limitation
    0.06
     whose
    0.06
    くらい
    0.06
     participa
    0.06
    𝕘
    0.06
     প্রকল্প
    0.06
     azok
    0.06
    Activations Density 0.001%

    No Known Activations