© 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. 117309
    Prev
    Next
    INDEX
    Explanations

    compounds, derivatives, analogs

    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
     जल्द
    -0.06
     الخم
    -0.06
    锈钢
    -0.06
     사람이
    -0.05
    ജ്
    -0.05
     żad
    -0.05
     مكان
    -0.05
     दिसते
    -0.05
     jerry
    -0.05
     לי
    -0.05
    POSITIVE LOGITS
     Aunque
    0.07
     convince
    0.06
     aqueous
    0.06
    🤪
    0.06
     মুখ্য
    0.06
     রচন
    0.06
     Mientras
    0.06
     Athletic
    0.06
     devotees
    0.06
    aqueous
    0.06
    Activations Density 0.040%

    No Known Activations