© 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. 128243
    Prev
    Next
    INDEX
    Explanations

    original words

    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
    唷
    -0.06
    -0.06
    自身
    -0.06
    ລ
    -0.06
     propri
    -0.06
     थोडे
    -0.06
     critic
    -0.06
    ）、
    -0.05
    支付
    -0.05
     pourrait
    -0.05
    POSITIVE LOGITS
     তাঁর
    0.06
    Тре
    0.06
     Practically
    0.06
     अत्याधुनिक
    0.06
    Го
    0.06
    écart
    0.06
    ਬਰ
    0.06
     as
    0.06
     første
    0.06
    Ту
    0.06
    Activations Density 0.012%

    No Known Activations