© 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. 118101
    Prev
    Next
    INDEX
    Explanations

    coding libraries and syntax

    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
    ത്തില്‍
    -0.07
    但也
    -0.07
     iedere
    -0.07
     such
    -0.06
    ത്തിൽ
    -0.06
     чтобы
    -0.06
     via
    -0.06
    但我
    -0.06
     каждый
    -0.06
     потому
    -0.06
    POSITIVE LOGITS
     граждан
    0.06
     সার্জ
    0.06
    casian
    0.05
     அடித்த
    0.05
     onay
    0.05
    மோ
    0.05
    목
    0.05
    দন
    0.05
     монасты
    0.05
     evidently
    0.05
    Activations Density 0.008%

    No Known Activations