© 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. 130003
    Prev
    Next
    INDEX
    Explanations

    also, has

    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
    অ
    -0.06
    曰
    -0.06
    तः
    -0.06
     difficile
    -0.06
    াপ্ত
    -0.06
     enunci
    -0.06
     socalled
    -0.05
     უნდა
    -0.05
     म्हणतात
    -0.05
     the
    -0.05
    POSITIVE LOGITS
     has
    0.07
    曾在
    0.07
     también
    0.07
     myös
    0.07
     également
    0.06
     भी
    0.06
    에
    0.06
     also
    0.06
     Ive
    0.06
     নিয়েও
    0.06
    Activations Density 0.018%

    No Known Activations