© 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. 128518
    Prev
    Next
    INDEX
    Explanations

    foreign language intensifiers

    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
     have
    -0.07
     by
    -0.07
    :
    -0.07
     sobre
    -0.06
     על
    -0.06
     over
    -0.06
     then
    -0.06
     about
    -0.06
     other
    -0.06
    多年
    -0.06
    POSITIVE LOGITS
     بسیار
    0.07
    还是很
    0.07
     foarte
    0.07
     ძალიან
    0.07
     довольно
    0.07
     vrlo
    0.07
    anggilan
    0.07
     davvero
    0.07
     ತುಂಬಾ
    0.06
    Sehr
    0.06
    Activations Density 0.001%

    No Known Activations