© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 128072
    Prev
    Next
    INDEX
    Explanations

    command syntax

    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
    Negative Logits
     전체
    -0.07
     Jeżeli
    -0.06
     مي‌
    -0.06
     Entonces
    -0.06
     новых
    -0.06
    ほうが
    -0.06
     jeżeli
    -0.06
    城区
    -0.06
     However
    -0.06
     violates
    -0.06
    POSITIVE LOGITS
    :
    0.07
    define
    0.06
    =
    0.06
    ;
    0.06
     use
    0.06
    使用
    0.06
     চমৎকার
    0.05
    @
    0.05
    的和
    0.05
    <
    0.05
    Activations Density 0.001%

    No Known Activations