© 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. 116456
    Prev
    Next
    INDEX
    Explanations

    employer tax, data, use

    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
    Algun
    -0.06
     একজনের
    -0.06
    有些人
    -0.06
     recipient
    -0.06
     self
    -0.06
     motivations
    -0.06
    april
    -0.06
     применя
    -0.06
    功能
    -0.06
     Javascript
    -0.06
    POSITIVE LOGITS
     their
    0.07
     empresarial
    0.07
     its
    0.06
     средне
    0.06
     jų
    0.06
     kanilang
    0.06
     Preferably
    0.06
     dette
    0.06
    中小
    0.06
     prophecies
    0.06
    Activations Density 0.007%

    No Known Activations