© 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. 117291
    Prev
    Next
    INDEX
    Explanations

    assigned 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
    由于
    -0.07
     अदालत
    -0.06
     tiga
    -0.06
     ثلاثة
    -0.06
    😭
    -0.06
    因为
    -0.06
     和
    -0.06
     $-\
    -0.06
     watermelon
    -0.06
    ইন্দ
    -0.06
    POSITIVE LOGITS
     REAL
    0.06
     अन्याय
    0.06
     কথিত
    0.06
     කාල
    0.06
    shadow
    0.05
     MORE
    0.05
     disponibili
    0.05
    舧
    0.05
     sockets
    0.05
     priorit
    0.05
    Activations Density 0.015%

    No Known Activations