© 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. 129198
    Prev
    Next
    INDEX
    Explanations

    // comments and code following them

    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
     enfrent
    -0.06
     sequência
    -0.06
    ј
    -0.06
     například
    -0.05
     Household
    -0.05
     निकलते
    -0.05
    人力
    -0.05
    ቀም
    -0.05
    KeyState
    -0.05
    nomina
    -0.05
    POSITIVE LOGITS
     own
    0.07
     diez
    0.07
     Five
    0.07
     FIVE
    0.07
     out
    0.07
     Out
    0.06
     cinque
    0.06
     चुनौ
    0.06
    Five
    0.06
     पांच
    0.06
    Activations Density 0.001%

    No Known Activations