© 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. 130379
    Prev
    Next
    INDEX
    Explanations

    mathematical equations

    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
    여러
    -0.06
     -,
    -0.06
    maktan
    -0.06
     -.
    -0.06
    ída
    -0.06
     মানুষদের
    -0.06
    たくさんの
    -0.06
     вер
    -0.06
     menschen
    -0.06
     で
    -0.05
    POSITIVE LOGITS
     a
    0.08
     więc
    0.06
     an
    0.06
     চৌ
    0.06
     at
    0.06
    的做法
    0.06
    typeof
    0.06
     switched
    0.06
     with
    0.06
     другому
    0.06
    Activations Density 0.007%

    No Known Activations