© 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. 118600
    Prev
    Next
    INDEX
    Explanations

    identification documents and cards

    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
     bevy
    -0.06
     collie
    -0.06
     некоторые
    -0.06
    我已经
    -0.06
    留学
    -0.06
     някои
    -0.06
     Perman
    -0.06
     hereafter
    -0.06
     entscheid
    -0.06
     gesetz
    -0.06
    POSITIVE LOGITS
     wäre
    0.08
     would
    0.07
     sarebbe
    0.07
    would
    0.07
     sarebbero
    0.06
     lenne
    0.06
    ద్ధ
    0.06
     olisi
    0.06
     desse
    0.06
     Regularly
    0.06
    Activations Density 0.001%

    No Known Activations