© 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. 120633
    Prev
    Next
    INDEX
    Explanations

    patent document descriptions

    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
     meisten
    -0.09
     многи
    -0.08
     двумя
    -0.08
     большинство
    -0.08
     большинстве
    -0.07
     बहुतेक
    -0.07
     многим
    -0.07
     многие
    -0.07
     większość
    -0.07
     plupart
    -0.07
    POSITIVE LOGITS
    ↵
    0.06
    ↵↵
    0.06
    ,
    0.06
    notas
    0.06
    :
    0.06
     noten
    0.06
    とにかく
    0.05
    知
    0.05
     usual
    0.05
    (
    0.05
    Activations Density 0.010%

    No Known Activations