© 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. 118377
    Prev
    Next
    INDEX
    Explanations

    ban on

    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
    severe
    -0.07
     скон
    -0.06
     severe
    -0.06
     their
    -0.06
     设置
    -0.06
     निवड
    -0.06
    減少
    -0.06
     severely
    -0.06
    CANCEL
    -0.06
     riduzione
    -0.06
    POSITIVE LOGITS
     using
    0.06
     प्रवेश
    0.06
     spanned
    0.06
     orgasm
    0.06
     wandered
    0.06
     usando
    0.06
    ிருந்தார்
    0.06
     જોઈ
    0.06
     توسط
    0.06
     curious
    0.06
    Activations Density 0.011%

    No Known Activations