© 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. 120938
    Prev
    Next
    INDEX
    Explanations

    character nicknames and affiliations

    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
    Negative Logits
     mildly
    -0.06
    พวก
    -0.06
     horribly
    -0.06
     Jurassic
    -0.06
     prevents
    -0.06
     تقریبا
    -0.06
     Poc
    -0.06
    лишком
    -0.06
     नव्ह
    -0.06
     extremely
    -0.06
    POSITIVE LOGITS
    ’!
    0.07
    !
    0.07
     caractéristique
    0.07
     utilizadas
    0.06
     характер
    0.06
     embossed
    0.06
     características
    0.06
     caratteristiche
    0.06
     уника
    0.06
     caract
    0.06
    Activations Density 0.026%

    No Known Activations