© 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. 127944
    Prev
    Next
    INDEX
    Explanations

    some / a few

    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
    于是
    -0.07
     już
    -0.06
    ajib
    -0.06
     así
    -0.06
     другой
    -0.06
     mundo
    -0.06
     आइसलैंड
    -0.06
    亟
    -0.06
     Harbor
    -0.06
     Requirement
    -0.06
    POSITIVE LOGITS
     કેટલાક
    0.07
    SOME
    0.07
     algunas
    0.07
     някои
    0.07
     niektor
    0.06
     일부
    0.06
     niektó
    0.06
     några
    0.06
     bazı
    0.06
     beberapa
    0.06
    Activations Density 0.001%

    No Known Activations