© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 128980
    Prev
    Next
    INDEX
    Explanations

    proper nouns and named entities

    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
     إلى
    -0.07
     عبد
    -0.06
     slowing
    -0.06
     heb
    -0.06
     tidak
    -0.06
     хло
    -0.06
     هلا
    -0.06
     قبل
    -0.06
     ಎಂದು
    -0.06
     elbow
    -0.06
    POSITIVE LOGITS
     nestled
    0.07
     необы
    0.07
    に関しては
    0.06
     NO
    0.06
    Above
    0.06
     Malgré
    0.05
     Above
    0.05
     grep
    0.05
    remarkable
    0.05
    については
    0.05
    Activations Density 0.062%

    No Known Activations