© 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. 116136
    Prev
    Next
    INDEX
    Explanations

    determines what how to be

    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
    ịch
    -0.06
     END
    -0.06
    iming
    -0.06
     SOFT
    -0.06
     меня
    -0.06
     constants
    -0.06
    FFF
    -0.06
     foll
    -0.06
     indecent
    -0.05
     nöt
    -0.05
    POSITIVE LOGITS
     militaire
    0.07
     militaires
    0.07
    military
    0.06
     military
    0.06
    Military
    0.06
     militares
    0.06
    測試
    0.06
     suur
    0.06
     decommission
    0.06
     steroids
    0.06
    Activations Density 0.018%

    No Known Activations