© 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. 117359
    Prev
    Next
    INDEX
    Explanations

    technical file and code context

    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
     was
    -0.09
     is
    -0.08
     has
    -0.07
     ebenso
    -0.07
     एक
    -0.07
     ငါ
    -0.06
     said
    -0.06
    至少
    -0.06
     went
    -0.06
     zumindest
    -0.06
    POSITIVE LOGITS
     Martin
    0.06
    素敵な
    0.06
    hasilan
    0.06
     прият
    0.05
     Appl
    0.05
    слан
    0.05
    หล
    0.05
    intercept
    0.05
     pages
    0.05
    交给
    0.05
    Activations Density 0.001%

    No Known Activations