© 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. 129512
    Prev
    Next
    INDEX
    Explanations

    Construction of

    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
     inaccur
    -0.07
     យើង
    -0.07
     revamped
    -0.07
     eagerness
    -0.07
    Durante
    -0.07
     vehement
    -0.07
     segura
    -0.07
     during
    -0.07
     of
    -0.07
    ุ่ม
    -0.07
    POSITIVE LOGITS
     configured
    0.05
    this
    0.05
    下一个
    0.05
    3
    0.05
    the
    0.05
     associated
    0.05
    कं
    0.05
    꼭
    0.05
    对应的
    0.05
    othe
    0.05
    Activations Density 0.004%

    No Known Activations