© 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. 120205
    Prev
    Next
    INDEX
    Explanations

    counting numbers

    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
    adds
    -0.06
     오른쪽
    -0.06
     adds
    -0.06
     вашего
    -0.06
     vostra
    -0.06
    adding
    -0.06
     votre
    -0.06
     вашу
    -0.06
     যুক্ত
    -0.06
     অঞ্চলের
    -0.05
    POSITIVE LOGITS
     two
    0.08
     രണ്ട്
    0.07
     দুটো
    0.07
     unprecedented
    0.07
     δύο
    0.07
     കിട
    0.07
    two
    0.06
    两个
    0.06
     nons
    0.06
     দুটি
    0.06
    Activations Density 0.001%

    No Known Activations