© 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. 116202
    Prev
    Next
    INDEX
    Explanations

    code statements and comments

    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
    記
    -0.06
     persönlichen
    -0.06
     guessing
    -0.06
    Ө
    -0.06
    َر
    -0.06
     personally
    -0.06
    とも
    -0.06
     terkait
    -0.05
    कूट
    -0.05
     berkaitan
    -0.05
    POSITIVE LOGITS
     широ
    0.07
     মাধ
    0.06
     unwavering
    0.06
     noticeably
    0.06
     одина
    0.06
    清楚
    0.06
     evacuate
    0.06
     evacuated
    0.06
     TLR
    0.06
    平凡
    0.06
    Activations Density 0.003%

    No Known Activations