© 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. 128196
    Prev
    Next
    INDEX
    Explanations

    slow, lag, seconds, speed, buffering

    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
     подготовке
    -0.06
     সংখ্যা
    -0.06
    ⏱
    -0.06
     จำนวน
    -0.06
     of
    -0.06
     method
    -0.06
     Integral
    -0.06
     one
    -0.06
    体积
    -0.06
    Integral
    -0.06
    POSITIVE LOGITS
     sluggish
    0.07
     embryonic
    0.07
    achron
    0.06
     aluno
    0.06
    embry
    0.06
    Provide
    0.06
     erratic
    0.06
     späteren
    0.06
     jitter
    0.06
    完美
    0.06
    Activations Density 0.023%

    No Known Activations