© 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. 117678
    Prev
    Next
    INDEX
    Explanations

    social media platforms

    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
    Especially
    -0.07
     especially
    -0.07
     Especially
    -0.07
     kiló
    -0.07
     especialmente
    -0.06
     परंपरागत
    -0.06
     recevoir
    -0.06
     म
    -0.06
     hereunder
    -0.06
     fejleszt
    -0.06
    POSITIVE LOGITS
    SOCIAL
    0.06
    変化
    0.06
     شناخت
    0.06
    这样做
    0.06
     allah
    0.06
    __'
    0.06
    ർട്ട
    0.06
     নিজেকে
    0.06
    aclysm
    0.06
     you
    0.06
    Activations Density 0.002%

    No Known Activations