© 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. 120783
    Prev
    Next
    INDEX
    Explanations

    author signing original works

    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
     adorable
    -0.07
    adorable
    -0.07
    Adorable
    -0.06
     convincingly
    -0.06
     बर्फ
    -0.06
     Allgemeinen
    -0.06
    相应
    -0.06
     systèmes
    -0.06
     cooled
    -0.06
     demostrado
    -0.06
    POSITIVE LOGITS
    原作
    0.08
     intentions
    0.08
    intended
    0.08
     originally
    0.07
     ursprünglich
    0.07
     intended
    0.07
    Originally
    0.07
     originalmente
    0.07
    原
    0.06
     வண்ணம்
    0.06
    Activations Density 0.034%

    No Known Activations