© 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. 116599
    Prev
    Next
    INDEX
    Explanations

    automated measurement and analysis

    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
    醸
    -0.06
    advertising
    -0.06
     research
    -0.06
     Research
    -0.06
     RESEARCH
    -0.06
    emf
    -0.06
     Stealth
    -0.06
    दर्श
    -0.06
     иде
    -0.06
     ідэ
    -0.06
    POSITIVE LOGITS
     otomatik
    0.07
     algorithmic
    0.07
     automated
    0.07
     computerized
    0.07
     automatis
    0.07
     automata
    0.06
     automatique
    0.06
     updates
    0.06
     автомати
    0.06
     onların
    0.06
    Activations Density 0.008%

    No Known Activations