© 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. 116203
    Prev
    Next
    INDEX
    Explanations

    young [person]

    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
     aged
    -0.06
     ۲۰
    -0.06
     age
    -0.06
     ١
    -0.06
     ٢
    -0.06
     такими
    -0.06
     initial
    -0.06
     travaille
    -0.06
     leeftijd
    -0.06
    高达
    -0.06
    POSITIVE LOGITS
    料理
    0.06
    Preprocessing
    0.06
     Ce
    0.06
     inkluder
    0.06
     premed
    0.06
     چیزی
    0.06
    ដើម្បី
    0.06
    淆
    0.06
     bizony
    0.06
     If
    0.06
    Activations Density 0.012%

    No Known Activations