© 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. 117028
    Prev
    Next
    INDEX
    Explanations

    want to use the

    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
     cercando
    -0.06
     توضیح
    -0.06
    aditional
    -0.06
    積極的に
    -0.06
    找到
    -0.06
     ಸಹಾಯ
    -0.06
     શોધ
    -0.06
     जरुर
    -0.06
    !?
    -0.06
     finding
    -0.06
    POSITIVE LOGITS
     instead
    0.07
     отсутствие
    0.07
    Instead
    0.07
     মার্কে
    0.06
     вероятность
    0.06
     lancio
    0.06
    Your
    0.06
     менее
    0.06
     aproximadamente
    0.06
    absence
    0.06
    Activations Density 0.009%

    No Known Activations