© 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. 128809
    Prev
    Next
    INDEX
    Explanations

    Manifest Destiny, Cherry Creek

    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
     যথা
    -0.06
     плюс
    -0.06
     مختلف
    -0.06
     სხვა
    -0.06
     いつ
    -0.06
     wichtigsten
    -0.06
     និង
    -0.06
     THIS
    -0.06
     ส
    -0.06
     기존
    -0.06
    POSITIVE LOGITS
     the
    0.07
    ❓
    0.06
     three
    0.06
    借鉴
    0.06
    残念
    0.06
    during
    0.06
    ⁉
    0.06
    著名的
    0.06
    ek
    0.06
    (*)
    0.06
    Activations Density 0.008%

    No Known Activations