© 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. 116155
    Prev
    Next
    INDEX
    Explanations

    HTML 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
     અથવા
    -0.09
     ወይም
    -0.08
     можно
    -0.08
     alebo
    -0.08
     hoặc
    -0.07
     или
    -0.07
     مثلا
    -0.07
     혹은
    -0.07
     أو
    -0.07
     ಅಥವಾ
    -0.07
    POSITIVE LOGITS
     additional
    0.07
     sebagian
    0.06
    additional
    0.06
    来源于
    0.06
    に関しては
    0.06
     portions
    0.06
     díky
    0.05
     unrelated
    0.05
    ////////////////
    0.05
     sobretudo
    0.05
    Activations Density 0.005%

    No Known Activations