© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 115878
    Prev
    Next
    INDEX
    Explanations

    similarity and likeness

    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
    Negative Logits
     অধিকাংশ
    -0.07
     Somewhat
    -0.07
    Although
    -0.07
    Because
    -0.06
     somewhat
    -0.06
    these
    -0.06
    基本的に
    -0.06
    Warranty
    -0.06
     เพราะ
    -0.06
     principle
    -0.06
    POSITIVE LOGITS
     an
    0.07
    预
    0.06
    撓
    0.06
    ,/
    0.06
     FET
    0.06
     convicted
    0.06
    𝙎
    0.05
     হারানোর
    0.05
    ])){
    0.05
     그는
    0.05
    Activations Density 0.028%

    No Known Activations