© 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. 117679
    Prev
    Next
    INDEX
    Explanations

    date or numbers following special characters

    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
     wealthy
    -0.06
     wonderland
    -0.06
     celebrated
    -0.06
     দৃষ্টান্ত
    -0.06
     you
    -0.05
    You
    -0.05
     vyst
    -0.05
    !!
    -0.05
     You
    -0.05
    উনি
    -0.05
    POSITIVE LOGITS
     Beschreibung
    0.08
     호출
    0.08
     तीन
    0.07
     σε
    0.07
     이런
    0.07
     एकमात्र
    0.07
    給
    0.07
     등
    0.07
    bbero
    0.07
     조금
    0.06
    Activations Density 0.011%

    No Known Activations