© 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. 117202
    Prev
    Next
    INDEX
    Explanations

    center/length

    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
    หาก
    -0.06
    னால்
    -0.06
    Inspector
    -0.06
     ಕೇಳ
    -0.06
     лег
    -0.06
     fabricating
    -0.06
     говоря
    -0.06
    Noah
    -0.06
    Caso
    -0.06
     якщо
    -0.06
    POSITIVE LOGITS
     Personnel
    0.07
     methotrexate
    0.07
     stopni
    0.06
     totals
    0.06
     during
    0.06
     gradually
    0.06
     initially
    0.06
     Optional
    0.06
    三十
    0.06
     During
    0.06
    Activations Density 0.003%

    No Known Activations