© 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. 128235
    Prev
    Next
    INDEX
    Explanations

    receptor antagonists, azole, butylbromide, inhibitors suppress

    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
    長時間
    -0.07
    叹
    -0.06
    }}
    -0.06
     mellett
    -0.06
    ̉i
    -0.06
     Œ
    -0.06
     پوست
    -0.06
     ሁኔታ
    -0.06
     OrderedDict
    -0.06
     representative
    -0.05
    POSITIVE LOGITS
     prolific
    0.07
     бетон
    0.06
     skyrocketed
    0.06
     skyrocketing
    0.06
    ния
    0.06
     Educators
    0.06
     Shower
    0.06
     يمكنك
    0.06
    もお
    0.06
     
    0.06
    Activations Density 0.005%

    No Known Activations