© 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. 119221
    Prev
    Next
    INDEX
    Explanations

    stop crowing or three games

    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
    诸多
    -0.07
     высокая
    -0.06
    Text
    -0.06
     numerosas
    -0.06
     zahlreiche
    -0.06
    などで
    -0.06
    https
    -0.06
     ray
    -0.06
     vence
    -0.06
     высокие
    -0.06
    POSITIVE LOGITS
     Puedes
    0.07
     unskilled
    0.07
    improve
    0.07
     collaborates
    0.07
     தேர்ந்தெடுக்க
    0.07
     Noch
    0.06
     அவர்களை
    0.06
    罵
    0.06
     Einstein
    0.06
     修改
    0.06
    Activations Density 0.006%

    No Known Activations