© 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. 119983
    Prev
    Next
    INDEX
    Explanations

    license or custom functionality

    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
    その
    -0.07
     equivalente
    -0.07
    equivalent
    -0.06
     laissant
    -0.06
     sonrası
    -0.06
     mientras
    -0.06
     特
    -0.06
     equivalent
    -0.06
    raintes
    -0.06
     स्पेशल
    -0.06
    POSITIVE LOGITS
     úspě
    0.07
     multiple
    0.07
     démontré
    0.07
     ponieważ
    0.06
    obucket
    0.06
     تعدد
    0.06
    何时
    0.06
    可靠
    0.06
     Multiple
    0.06
     множе
    0.06
    Activations Density 0.001%

    No Known Activations