© 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. 128312
    Prev
    Next
    INDEX
    Explanations

    only

    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
    デフォルト
    -0.06
     among
    -0.06
    外
    -0.06
    いま
    -0.06
    део
    -0.06
     {\
    -0.06
    重要な
    -0.06
     Edward
    -0.05
     গ্রন্থে
    -0.05
     tides
    -0.05
    POSITIVE LOGITS
     pouze
    0.07
     hanya
    0.06
     vertrou
    0.06
     детям
    0.06
     только
    0.06
    直到
    0.06
     panicked
    0.06
     merely
    0.06
     없이
    0.06
     uniquement
    0.06
    Activations Density 0.007%

    No Known Activations