© 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. 116725
    Prev
    Next
    INDEX
    Explanations

    dropdown menus

    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
    選擇
    -0.08
     选择
    -0.08
     scegliere
    -0.07
     choose
    -0.07
    选择
    -0.07
    เลือก
    -0.07
    𝙀
    -0.07
     favorita
    -0.06
     फिर
    -0.06
     choisissez
    -0.06
    POSITIVE LOGITS
     salud
    0.06
    pens
    0.06
     our
    0.06
     HERE
    0.06
    ([-
    0.06
     metaphor
    0.05
     फंक्शन
    0.05
     oppressed
    0.05
     HEALTH
    0.05
     aéri
    0.05
    Activations Density 0.006%

    No Known Activations