© 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. 120576
    Prev
    Next
    INDEX
    Explanations

    html meta tags and attributes

    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
    である
    -0.07
     including
    -0.06
    Hình
    -0.06
     einschließlich
    -0.06
    thomas
    -0.06
     Hospital
    -0.06
     včetně
    -0.06
    にある
    -0.06
    ख्यात
    -0.05
     interment
    -0.05
    POSITIVE LOGITS
     করে
    0.07
     इनसे
    0.06
    烔
    0.06
     reaksi
    0.06
     odgov
    0.05
    getDefault
    0.05
    वार्
    0.05
     ওদের
    0.05
    arino
    0.05
    यहां
    0.05
    Activations Density 0.001%

    No Known Activations