© 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. 130428
    Prev
    Next
    INDEX
    Explanations

    Q: or QC:

    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
     new
    -0.06
     topology
    -0.06
     a
    -0.06
     an
    -0.06
    FILE
    -0.06
    resin
    -0.06
    äsident
    -0.05
    дный
    -0.05
     British
    -0.05
     Topology
    -0.05
    POSITIVE LOGITS
     evitando
    0.07
     evitar
    0.07
     porque
    0.07
     panjang
    0.06
     descrito
    0.06
     大きい
    0.06
    避免
    0.06
     colocando
    0.06
     কত
    0.06
     между
    0.06
    Activations Density 0.001%

    No Known Activations