© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 118875
    Prev
    Next
    INDEX
    Explanations

    symbols or non-English 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
    仅仅
    -0.07
     только
    -0.07
    也就
    -0.06
       
    -0.06
     £
    -0.06
     буквально
    -0.06
    activities
    -0.06
    gameObject
    -0.06
     gdzie
    -0.06
     proving
    -0.05
    POSITIVE LOGITS
     ನಮ್ಮ
    0.07
     vores
    0.07
     சுதந்திர
    0.06
     бажа
    0.06
    incere
    0.06
    jfif
    0.06
     compromet
    0.06
    东京
    0.06
    roke
    0.06
     باقی
    0.06
    Activations Density 0.001%

    No Known Activations