© 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. 120052
    Prev
    Next
    INDEX
    Explanations

    plugin/load/digital methodology

    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
     필요한
    -0.07
     potřeb
    -0.06
     इंपोर्टेंट
    -0.06
     needed
    -0.06
     किफायती
    -0.06
     potreb
    -0.06
     इंपॉर्टेंट
    -0.06
     গুরুত্বপূর্ণ
    -0.06
     potrzeb
    -0.06
    你
    -0.06
    POSITIVE LOGITS
     bổ
    0.06
     ciertos
    0.06
     songwriters
    0.06
     questionnaires
    0.05
     eigenlijk
    0.05
     seclusion
    0.05
     aggressiveness
    0.05
     legalized
    0.05
     bandeja
    0.05
    らは
    0.05
    Activations Density 0.002%

    No Known Activations