© 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. 128880
    Prev
    Next
    INDEX
    Explanations

    special characters and their following 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
     compartilh
    -0.07
    şan
    -0.06
     incendio
    -0.06
     =(
    -0.06
    共享
    -0.06
     now
    -0.06
     হারানোর
    -0.06
     Atención
    -0.06
     доктор
    -0.06
    کیل
    -0.06
    POSITIVE LOGITS
     Also
    0.07
    Also
    0.07
    these
    0.06
     could
    0.06
     اكو
    0.06
     those
    0.06
     Naj
    0.06
    wk
    0.05
    чём
    0.05
    出来る
    0.05
    Activations Density 0.001%

    No Known Activations