© 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. 118196
    Prev
    Next
    INDEX
    Explanations

    A: or Answer:

    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
     muscles
    -0.07
     Otherwise
    -0.06
     einem
    -0.06
    Otherwise
    -0.06
     môže
    -0.06
     może
    -0.06
     مہارت
    -0.06
     assume
    -0.06
     capacità
    -0.06
    न्हे
    -0.06
    POSITIVE LOGITS
    prot
    0.06
    也都
    0.06
     jo
    0.06
     heretofore
    0.06
     помимо
    0.06
    ifying
    0.06
     of
    0.06
    assess
    0.06
    el
    0.06
     besides
    0.06
    Activations Density 0.011%

    No Known Activations