© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 118733
    Prev
    Next
    INDEX
    Explanations

    citations and references

    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
     then
    -0.07
     নানান
    -0.07
     have
    -0.07
     আজকাল
    -0.06
     많이
    -0.06
     make
    -0.06
     ثم
    -0.06
     sporadically
    -0.06
     હાલ
    -0.06
     various
    -0.06
    POSITIVE LOGITS
     सच्चा
    0.07
     HOSPITAL
    0.06
     japonés
    0.06
    (*)
    0.06
    WWW
    0.06
    บอก
    0.06
     hospital
    0.06
    வையும்
    0.06
     nursing
    0.06
     aseguró
    0.06
    Activations Density 0.001%

    No Known Activations