© 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. 117962
    Prev
    Next
    INDEX
    Explanations

    hydroxy functional groups

    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
     komfort
    -0.06
     erine
    -0.06
     pohod
    -0.06
     document
    -0.06
     উক
    -0.06
     asshole
    -0.05
    کی
    -0.05
     incluindo
    -0.05
     voldo
    -0.05
     oke
    -0.05
    POSITIVE LOGITS
    strMeal
    0.07
    regarded
    0.06
     mấy
    0.06
     специальных
    0.06
     competing
    0.06
     Beside
    0.06
     Roosevelt
    0.06
     Critics
    0.06
    restassured
    0.06
     Gruppe
    0.06
    Activations Density 0.020%

    No Known Activations