© 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. 120284
    Prev
    Next
    INDEX
    Explanations

    HTML tags like button, p, element

    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
     most
    -0.08
    分野
    -0.06
     subsets
    -0.06
     분야
    -0.06
     distinct
    -0.06
     जस्ट
    -0.06
     birthday
    -0.06
     songwriters
    -0.06
    分别
    -0.06
     नसी
    -0.06
    POSITIVE LOGITS
     तीसरे
    0.06
    वतात
    0.06
     autre
    0.06
     terceira
    0.06
    alja
    0.06
     seu
    0.06
     evitar
    0.06
     evitare
    0.05
     terceiro
    0.05
     expatri
    0.05
    Activations Density 0.001%

    No Known Activations