© 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. 116273
    Prev
    Next
    INDEX
    Explanations

    programming code and commands

    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
     with
    -0.09
     or
    -0.08
    注重
    -0.07
     encir
    -0.06
     dengan
    -0.06
    Cette
    -0.06
     by
    -0.06
    ’
    -0.06
     elabor
    -0.06
     với
    -0.06
    POSITIVE LOGITS
     référence
    0.07
    当量
    0.07
     когда
    0.07
     khoảng
    0.07
    acin
    0.07
     cuando
    0.07
     عندما
    0.07
     όταν
    0.07
     及
    0.06
     לאחר
    0.06
    Activations Density 0.013%

    No Known Activations