© 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. 118082
    Prev
    Next
    INDEX
    Explanations

    number or size

    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
     ingrédients
    -0.06
    ুব্ধ
    -0.06
    蹲
    -0.06
     buildup
    -0.06
     obowią
    -0.05
     নিজেদের
    -0.05
     idéale
    -0.05
    囉
    -0.05
     police
    -0.05
     עבור
    -0.05
    POSITIVE LOGITS
     정책
    0.07
     कौन
    0.07
     safer
    0.06
    вають
    0.06
     sequence
    0.06
     сказала
    0.06
     repeatable
    0.06
     करने
    0.06
     highest
    0.06
     Ends
    0.06
    Activations Density 0.003%

    No Known Activations