© 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. 116931
    Prev
    Next
    INDEX
    Explanations

    file extensions

    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
     type
    -0.07
     Most
    -0.06
     Type
    -0.06
     decorations
    -0.06
     most
    -0.06
    FAKE
    -0.06
    簡単に
    -0.06
     SERVICE
    -0.06
     shot
    -0.06
     Several
    -0.06
    POSITIVE LOGITS
     weil
    0.07
    이었다
    0.06
    appui
    0.06
    ೂರ್ವ
    0.06
     kerana
    0.06
    เนื่อง
    0.06
    だった
    0.06
     dilaksanakan
    0.06
     underpinning
    0.06
    obby
    0.06
    Activations Density 0.009%

    No Known Activations