© 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. 118461
    Prev
    Next
    INDEX
    Explanations

    numbers followed by text

    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
     partner
    -0.08
     seemed
    -0.07
     feminist
    -0.07
     partners
    -0.07
     периоди
    -0.06
     parecía
    -0.06
     periodical
    -0.06
     moż
    -0.06
     seeming
    -0.06
     runtime
    -0.06
    POSITIVE LOGITS
     오후
    0.06
     gmin
    0.06
    बारा
    0.06
     quando
    0.05
     cuando
    0.05
     ভুল
    0.05
     зад
    0.05
     ग्रामीण
    0.05
    bic
    0.05
     முனை
    0.05
    Activations Density 0.001%

    No Known Activations