© 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. 120287
    Prev
    Next
    INDEX
    Explanations

    tipping point, wave live, so far, caveat

    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
     questions
    -0.07
    Questions
    -0.07
     questioning
    -0.06
     Fully
    -0.06
     scorching
    -0.06
     video
    -0.06
     Questions
    -0.06
    Fully
    -0.06
     vidéo
    -0.06
    写真は
    -0.06
    POSITIVE LOGITS
     claimed
    0.06
     monotone
    0.06
    incredible
    0.06
    功率
    0.06
     fantastical
    0.06
     organised
    0.06
     incredible
    0.06
     organized
    0.06
     inferred
    0.06
     pregnant
    0.06
    Activations Density 0.001%

    No Known Activations