© 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. 120015
    Prev
    Next
    INDEX
    Explanations

    compilation and foreign words

    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
     occasionally
    -0.07
    เพิ่มเติม
    -0.06
    认可
    -0.06
    engaruhi
    -0.06
    聘
    -0.06
     updates
    -0.06
     several
    -0.06
     also
    -0.06
    気に入
    -0.06
     kerana
    -0.06
    POSITIVE LOGITS
     для
    0.07
    для
    0.06
     destruction
    0.06
    现在
    0.06
    맏
    0.06
     demethyl
    0.06
     destruir
    0.06
     için
    0.06
     elimination
    0.06
     punishment
    0.06
    Activations Density 0.003%

    No Known Activations