© 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. 119905
    Prev
    Next
    INDEX
    Explanations

    claims, assumptions, hypotheses

    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
     किसी
    -0.07
     at
    -0.07
     any
    -0.07
     characterizes
    -0.07
     любой
    -0.06
     berichtet
    -0.06
     information
    -0.06
     exag
    -0.06
    定义
    -0.06
     laporan
    -0.06
    POSITIVE LOGITS
    ailable
    0.06
    😅
    0.06
    兼容
    0.06
     trzeba
    0.05
     entail
    0.05
     ដោយ
    0.05
    হা
    0.05
     entails
    0.05
    的效果
    0.05
     require
    0.05
    Activations Density 0.007%

    No Known Activations