© 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. 120529
    Prev
    Next
    INDEX
    Explanations

    of a / the

    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
     this
    -0.10
    this
    -0.08
     my
    -0.07
    processes
    -0.07
    感受到
    -0.07
     цього
    -0.06
     هذا
    -0.06
     your
    -0.06
     our
    -0.06
     tohoto
    -0.06
    POSITIVE LOGITS
     ryzy
    0.07
    ாந்து
    0.06
     النسبيه
    0.06
     მნიშვნელ
    0.06
     القيمه
    0.06
     القسمه
    0.06
     والصلاه
    0.06
     дода
    0.06
    یسم
    0.06
    銹
    0.06
    Activations Density 0.024%

    No Known Activations