© 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. 120424
    Prev
    Next
    INDEX
    Explanations

    html/code structure or tags

    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
    উঠ
    -0.06
     অংশগ্রহণ
    -0.06
     autres
    -0.06
    emplates
    -0.06
     गोद
    -0.06
    ):
    -0.06
    মুসলিম
    -0.06
     innan
    -0.06
    instit
    -0.06
     inclus
    -0.05
    POSITIVE LOGITS
     डिजा
    0.06
     অবশ্য
    0.05
     }.
    0.05
     kèm
    0.05
    forEach
    0.05
    尊敬
    0.05
     magick
    0.05
     للنساء
    0.05
    どう
    0.05
     Misch
    0.05
    Activations Density 0.004%

    No Known Activations