© 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. 119615
    Prev
    Next
    INDEX
    Explanations

    after a word or followed by specific 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
     unsatisfactory
    -0.07
     withdrawals
    -0.06
     热
    -0.06
     Metabolism
    -0.06
     yani
    -0.06
     withdrawal
    -0.06
    の日
    -0.06
     производится
    -0.06
     beschikbaar
    -0.06
     withdraw
    -0.06
    POSITIVE LOGITS
    এটি
    0.06
     visiting
    0.06
     Visiting
    0.06
    assist
    0.06
    copied
    0.06
     assist
    0.06
     Focusing
    0.06
    助理
    0.05
    helper
    0.05
     contatto
    0.05
    Activations Density 0.012%

    No Known Activations