© 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. 129048
    Prev
    Next
    INDEX
    Explanations

    posts about topics

    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
     یک
    -0.07
     feme
    -0.06
     MANY
    -0.06
    文章
    -0.06
     pierws
    -0.06
    ច្រើន
    -0.06
     nitrog
    -0.06
     первого
    -0.06
     एक
    -0.06
     आपने
    -0.06
    POSITIVE LOGITS
     to
    0.07
    ?
    0.06
    依照
    0.06
    providing
    0.06
    jin
    0.06
     Craigslist
    0.06
    rera
    0.06
    事实上
    0.06
     குறிப்பிட்ட
    0.06
    toFixed
    0.06
    Activations Density 0.012%

    No Known Activations