© 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. 119948
    Prev
    Next
    INDEX
    Explanations

    must be

    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
    需要
    -0.07
    所需的
    -0.07
     según
    -0.06
    ကြောင်း
    -0.06
     relapse
    -0.06
     hatta
    -0.06
    ͆
    -0.06
    ベルト
    -0.06
    決
    -0.06
    থানি
    -0.06
    POSITIVE LOGITS
     wonderful
    0.07
     wonderfully
    0.07
     the
    0.07
     our
    0.07
     it
    0.06
    (?)
    0.06
     magnificent
    0.06
     comprehensive
    0.06
     সাম্প্রতিক
    0.06
     (?)
    0.06
    Activations Density 0.017%

    No Known Activations