© 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. 120076
    Prev
    Next
    INDEX
    Explanations

    html/xhtml doctype declarations

    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
    🦋
    -0.07
     сложности
    -0.06
     schönsten
    -0.06
     tích
    -0.06
     ପ
    -0.06
     clums
    -0.06
    影響
    -0.06
    مد
    -0.05
    率先
    -0.05
    (("
    -0.05
    POSITIVE LOGITS
     a
    0.08
     you
    0.07
    을
    0.07
     your
    0.07
     who
    0.07
    8
    0.06
    7
    0.06
     está
    0.06
    de
    0.06
     datetime
    0.06
    Activations Density 0.002%

    No Known Activations