© 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. 116698
    Prev
    Next
    INDEX
    Explanations

    conditional probability and statistics

    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
     различи
    -0.06
    gameObject
    -0.06
    ゆっくり
    -0.06
     protected
    -0.06
    Ei
    -0.06
     protegido
    -0.05
     competitive
    -0.05
     ছিন
    -0.05
     successive
    -0.05
    福利
    -0.05
    POSITIVE LOGITS
     ainsi
    0.06
     haces
    0.06
     biasanya
    0.06
     ý
    0.06
     많이
    0.06
     hy
    0.06
     theatrical
    0.06
     있지만
    0.06
     hacemos
    0.05
     facteur
    0.05
    Activations Density 0.001%

    No Known Activations