© 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. 128186
    Prev
    Next
    INDEX
    Explanations

    code block delimiters

    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
     although
    -0.06
     તથા
    -0.06
     වශයෙන්
    -0.06
     වශ
    -0.06
    PartOf
    -0.06
     அதிச
    -0.06
     একটা
    -0.06
    形態
    -0.06
     ઉપર
    -0.06
    รูปแบบ
    -0.06
    POSITIVE LOGITS
     ({
    0.06
     περισσότε
    0.06
     zapewn
    0.06
     memastikan
    0.06
    mé
    0.06
     табли
    0.06
     tenter
    0.06
     therein
    0.06
     unbeatable
    0.06
    années
    0.06
    Activations Density 0.009%

    No Known Activations