© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 118928
    Prev
    Next
    INDEX
    Explanations

    code delimiters 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
    の
    -0.08
     On
    -0.07
     nella
    -0.07
     на
    -0.06
    に
    -0.06
     في
    -0.06
     в
    -0.06
     على
    -0.06
     în
    -0.06
    의
    -0.06
    POSITIVE LOGITS
     simply
    0.07
     amazement
    0.07
     chasing
    0.06
     включая
    0.06
     通过
    0.06
     фикси
    0.06
     another
    0.06
     including
    0.06
     +
    0.06
     trying
    0.06
    Activations Density 0.010%

    No Known Activations