© 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
    2. Gemma-4-31B
    3. 30-RES-MATRYOSHKA-131K
    4. 130288
    Prev
    Next
    INDEX
    Explanations

    string variable, file read

    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
    either
    -0.07
    メートル
    -0.06
    変更
    -0.06
     examples
    -0.06
     ممکن
    -0.06
    に合わせて
    -0.06
    ご確認
    -0.06
    Hyderabad
    -0.06
     modifications
    -0.06
    示例
    -0.06
    POSITIVE LOGITS
    各大
    0.06
     fiecare
    0.06
    各
    0.06
     each
    0.06
     পোক
    0.06
    urta
    0.06
    new
    0.05
     />);
    0.05
     Can
    0.05
    printf
    0.05
    Activations Density 0.014%

    No Known Activations