© 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. 119906
    Prev
    Next
    INDEX
    Explanations

    HTML tags and templating elements

    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
    two
    -0.07
    4
    -0.06
    3
    -0.06
    9
    -0.06
    ভের
    -0.06
    5
    -0.06
     অথবা
    -0.05
     আরম্ভ
    -0.05
    Ι
    -0.05
     thật
    -0.05
    POSITIVE LOGITS
     diversas
    0.07
    けば
    0.07
     numerous
    0.07
     each
    0.07
     çeşitli
    0.06
    ว่า
    0.06
    量が
    0.06
     listing
    0.06
     محصولات
    0.06
     اقدامات
    0.06
    Activations Density 0.014%

    No Known Activations