© 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. 116302
    Prev
    Next
    INDEX
    Explanations

    kitchen island

    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
    引用
    -0.07
     importation
    -0.06
    subsection
    -0.06
     bian
    -0.06
     அடிப்பட
    -0.06
     Czar
    -0.05
    check
    -0.05
    Check
    -0.05
    Several
    -0.05
     PHA
    -0.05
    POSITIVE LOGITS
     informal
    0.07
     propriété
    0.06
     trochę
    0.06
    dés
    0.06
     Tipo
    0.06
    Rio
    0.06
     lager
    0.06
    setProperty
    0.06
     suure
    0.06
     dés
    0.06
    Activations Density 0.033%

    No Known Activations