© 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. 117149
    Prev
    Next
    INDEX
    Explanations

    item id references

    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
     τελευτα
    -0.06
     दिसत
    -0.06
    Recent
    -0.06
    despite
    -0.06
     Prevention
    -0.06
     ранее
    -0.06
     жі
    -0.06
     recent
    -0.06
    逐漸
    -0.06
    逐渐
    -0.06
    POSITIVE LOGITS
     supremely
    0.06
     للإ
    0.06
     يعني
    0.06
     name
    0.06
    貴重
    0.05
     планы
    0.05
     klicken
    0.05
     обратиться
    0.05
    ご
    0.05
    ubes
    0.05
    Activations Density 0.010%

    No Known Activations