© 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. 116336
    Prev
    Next
    INDEX
    Explanations

    look forward to

    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
     হারানোর
    -0.06
    níky
    -0.06
     herhangi
    -0.06
     pretence
    -0.06
     Diarsipkan
    -0.06
    】,
    -0.06
     }[
    -0.05
     önemli
    -0.05
     esth
    -0.05
    해
    -0.05
    POSITIVE LOGITS
    実施
    0.07
    を実施
    0.07
    应该是
    0.06
     dilaksanakan
    0.06
    蔬菜
    0.06
     চিকিৎসার
    0.06
     Relaxation
    0.06
     źród
    0.06
     effectively
    0.06
     извър
    0.06
    Activations Density 0.009%

    No Known Activations