© 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
    2. Gemma-4-31B
    3. 30-RES-MATRYOSHKA-131K
    4. 128438
    Prev
    Next
    INDEX
    Explanations

    media and advertising kit

    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
     hoses
    -0.06
     канала
    -0.06
     mecz
    -0.06
     chronically
    -0.06
    matched
    -0.06
     `${
    -0.06
    తూ
    -0.06
     memasuki
    -0.06
     ids
    -0.06
    then
    -0.06
    POSITIVE LOGITS
     खूबसूरत
    0.06
     ↑
    0.06
     नक्सलियों
    0.06
     Änderungen
    0.05
     બંને
    0.05
     பகுதிக
    0.05
    你怎么
    0.05
     빨리
    0.05
     झाले
    0.05
    Speaking
    0.05
    Activations Density 0.041%

    No Known Activations