© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 118505
    Prev
    Next
    INDEX
    Explanations

    gene targeting and knockout

    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
     those
    -0.07
    合う
    -0.07
     some
    -0.06
     powodu
    -0.06
     زیادی
    -0.06
    increases
    -0.06
     girls
    -0.06
    洩
    -0.06
     ખરી
    -0.06
     reproduce
    -0.06
    POSITIVE LOGITS
     imperative
    0.06
    ليف
    0.06
    実験
    0.06
     pivotal
    0.06
    关键
    0.06
    關鍵
    0.06
    試験
    0.06
     experiments
    0.06
     방법
    0.06
    实验
    0.06
    Activations Density 0.019%

    No Known Activations