© 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. 129115
    Prev
    Next
    INDEX
    Explanations

    exhibitions

    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
     at
    -0.07
     each
    -0.06
     James
    -0.06
     Miller
    -0.06
     tilbake
    -0.06
     featuring
    -0.05
     lainnya
    -0.05
    ائِ
    -0.05
     McCann
    -0.05
     fundamental
    -0.05
    POSITIVE LOGITS
     Chaplain
    0.07
     држа
    0.06
    だけ
    0.06
    これは
    0.06
     windfall
    0.06
     Komb
    0.06
    最初の
    0.06
     herkes
    0.06
     uninter
    0.06
     komplette
    0.06
    Activations Density 0.049%

    No Known Activations