© 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. 127988
    Prev
    Next
    INDEX
    Explanations

    vendor, include, synthesis, shorter, considerably

    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
    перед
    -0.06
    namely
    -0.06
    ার্জন
    -0.06
    ebay
    -0.06
    <
    -0.05
     Pum
    -0.05
    [-]
    -0.05
     masculino
    -0.05
     viens
    -0.05
     correspondence
    -0.05
    POSITIVE LOGITS
     значительно
    0.07
    減少
    0.07
     शिश
    0.07
     увеличи
    0.07
     그는
    0.07
     zmniejs
    0.06
     considerably
    0.06
     만나
    0.06
     shorter
    0.06
     características
    0.06
    Activations Density 0.002%

    No Known Activations