© 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. 119859
    Prev
    Next
    INDEX
    Explanations

    code delimiters and keywords

    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
     on
    -0.08
     zusätzlich
    -0.06
     variously
    -0.06
    自己
    -0.06
     Zusätzlich
    -0.06
     in
    -0.06
     adhé
    -0.06
    別に
    -0.06
    之内
    -0.06
     내용을
    -0.06
    POSITIVE LOGITS
     সেজন্য
    0.06
    ঞ্চিত
    0.06
     মেঝে
    0.06
    及
    0.06
    .......
    0.06
     FIND
    0.06
     பாதிக்கப்பட்ட
    0.06
    низ
    0.05
     ..........
    0.05
     **
    0.05
    Activations Density 0.002%

    No Known Activations